Skip to content

Conversation

@obra
Copy link
Owner

@obra obra commented Oct 11, 2025

Summary

Extract and adapt problem-solving techniques from Amplifier's agent system into focused, composable skills.

New skills added:

  • 5 problem-solving techniques (simplification-cascades, collision-zone-thinking, meta-pattern-recognition, inversion-exercise, scale-game)
  • 1 dispatch skill (when-stuck flowchart)
  • 1 architecture skill (preserving-productive-tensions)
  • 1 research skill (tracing-knowledge-lineages)

Enhanced existing skills:

  • brainstorming: Added flexibility to revisit earlier phases
  • executing-plans: Added explicit blocker handling

Key improvements:

  • ~60 lines each with quick reference tables
  • Symptom-based when_to_use for discovery
  • Pattern-based triggers (not exact phrases)
  • Cross-referenced from brainstorming for discoverability
  • All pressure-tested with subagents

What Changed

Problem-Solving Skills (New)

  • simplification-cascades: Find one insight that eliminates multiple components
  • collision-zone-thinking: Force unrelated concepts together for breakthroughs
  • meta-pattern-recognition: Spot patterns appearing in 3+ domains
  • inversion-exercise: Flip assumptions to reveal alternatives
  • scale-game: Test at extremes to expose fundamental truths
  • when-stuck: Dispatch flowchart mapping stuck-symptoms to techniques

Architecture Skills (New)

  • preserving-productive-tensions: Preserve multiple valid approaches when context determines which is better

Research Skills (New)

  • tracing-knowledge-lineages: Understand why code exists before changing it

Workflow Skills (Enhanced)

  • brainstorming: Phases with "When to Revisit" - flexibility over rigid progression
  • executing-plans: Steps with "When to Stop" - blocker handling

Testing

All skills tested with RED-GREEN-REFACTOR methodology:

  • Baseline tests without skills showed natural behavior
  • Tests with skills verified compliance under pressure
  • Pressure scenarios included: sunk cost, time pressure, momentum bias
  • All skills passed final verification

Attribution

Skills derived from amplifier agents (commit 2adb63f):

  • insight-synthesizer → 5 problem-solving techniques
  • ambiguity-guardian → preserving-productive-tensions
  • knowledge-archaeologist → tracing-knowledge-lineages

See ABOUT.md files in each category for full attribution.

Summary by CodeRabbit

  • New Features

    • New skill guides: Collision-Zone Thinking, Inversion Exercise, Meta-Pattern Recognition, Scale Game, Simplification Cascades, When Stuck (dispatch), Tracing Knowledge Lineages, and Preserving Productive Tensions.
  • Improvements

    • Brainstorming: clarified non-linear flow, added “When to Revisit Earlier Phases,” simplified guidance.
    • Executing Plans: added “When to Stop and Ask for Help” and “When to Revisit Earlier Steps,” reorganized reminders.
  • Documentation

    • Added attribution pages for Architecture, Problem-Solving, and Research skill sets.

obra added 9 commits October 10, 2025 11:58
**Mode-switching enhancements:**
- Update brainstorming skill with flexible UNDERSTANDING/EXPLORING/DESIGNING modes
- Update executing-plans skill with REVIEWING/EXECUTING/BLOCKED/REPORTING modes
- Add inline dot diagrams with full contextual labels for all valid transitions
- Enforce explicit mode switch announcements

**New architecture skills from amplifier patterns:**
- preserving-productive-tensions: Recognize when to preserve multiple valid approaches vs force resolution
- tracing-knowledge-lineages: Understand idea evolution to avoid repeating failures
- detecting-emergent-patterns: Cross-domain synthesis, collision-zone thinking, simplification cascades

All skills pressure-tested with subagents using RED-GREEN-REFACTOR methodology.
- Reference preserving-productive-tensions from brainstorming EXPLORING mode
- Reference detecting-emergent-patterns from brainstorming when stuck
- Reference tracing-knowledge-lineages from brainstorming before changes
- Reference tracing-knowledge-lineages from executing-plans REVIEWING mode

Makes new architecture skills discoverable through commonly-used workflows.
Replace 'ai_working/decisions/' with generic decision record locations
Use common locations instead of project-specific paths
**Restructure:**
- Split detecting-emergent-patterns (216 lines) into 5 focused skills (~60 lines each)
- Move tracing-lineages to skills/research/ (better category fit)
- Create skills/problem-solving/ category

**New problem-solving skills:**
- simplification-cascades: Find one insight that eliminates multiple components
- collision-zone-thinking: Force unrelated concepts together for breakthroughs
- meta-pattern-recognition: Spot patterns in 3+ domains
- inversion-exercise: Flip assumptions to reveal alternatives
- scale-game: Test at extremes to find fundamental limits
- when-stuck: Dispatch skill that maps stuck-symptoms to techniques

**Improvements:**
- Symptom-based when_to_use (what you'd actually think/feel)
- Quick reference tables for rapid scanning
- Pattern-based triggers (not exact phrase matching)
- Cross-references from brainstorming for discoverability

Each skill now: scannable in 30 seconds, applicable immediately, focused on one technique.
**Discovery enhancement:**
- Add Mandatory Workflow 4 to getting-started: "When Stuck"
- Creates path: getting-started → when-stuck dispatch → specific technique
- Prevents spinning wheels without seeking help

**Trigger clarity:**
- Replace phrase examples with pattern descriptions
- "Partner reveals constraint you didn't consider" (pattern) not "Oh, I forgot..." (phrase)
- Emphasizes NEW information that invalidates current context
- Prevents ambiguity between new constraints vs clarifications

Tested: All skills verified with subagents, triggers work correctly.
Agents don't search for skills when stuck, even with explicit workflow.
Trust organic discovery via symptom-based when_to_use instead.
Mode-switching was overcomplicated. Back to phases with explicit permission
to revisit earlier phases when constraints emerge or validation fails.

Simpler, clearer, preserves what worked.
Credit amplifier repo (github.com/microsoft/amplifier @ 2adb63f)
for agent patterns that inspired these skills.
@coderabbitai
Copy link

coderabbitai bot commented Oct 11, 2025

Walkthrough

Adds new documentation skills and attribution ABOUT pages across architecture, problem-solving, and research domains; updates two collaboration skills with version bumps and new guidance on revisiting steps and asking for help. Introduces multiple new problem-solving techniques and a dispatch guide; adds a research lineage-tracing skill and an architecture skill on preserving productive tensions.

Changes

Cohort / File(s) Summary of Changes
Architecture Attribution & Skills
skills/architecture/ABOUT.md, skills/architecture/preserving-productive-tensions/SKILL.md
Added attribution for Architecture Skills and a new skill on preserving productive tensions with criteria, patterns, red flags, and documentation guidelines.
Collaboration Updates
skills/collaboration/brainstorming/SKILL.md, skills/collaboration/executing-plans/SKILL.md
Version bumps to 2.1.0. Added guidance on revisiting phases/steps and when to stop and ask for help; minor text edits and reorganization.
Problem-Solving Attribution
skills/problem-solving/ABOUT.md
Added attribution detailing sources, derived agents/patterns, and adaptation notes.
Problem-Solving Techniques (New)
skills/problem-solving/collision-zone-thinking/SKILL.md, skills/problem-solving/inversion-exercise/SKILL.md, skills/problem-solving/meta-pattern-recognition/SKILL.md, skills/problem-solving/scale-game/SKILL.md, skills/problem-solving/simplification-cascades/SKILL.md
Added new skills with metadata, overviews, quick references, processes, examples, red flags, and reminders. Documentation only.
Problem-Solving Dispatch
skills/problem-solving/when-stuck/SKILL.md
Added a dispatch guide mapping stuck symptoms to techniques; includes a diagram, rules table, process, and combo guidance.
Research Attribution & Skill
skills/research/ABOUT.md, skills/research/tracing-knowledge-lineages/SKILL.md
Added research attribution and a new lineage-tracing skill with techniques, templates, search strategies, and red flags.

Sequence Diagram(s)

sequenceDiagram
  autonumber
  actor Practitioner
  participant Dispatch as When-Stuck Dispatch
  participant Technique as Selected Technique
  participant Output as Outcome

  Practitioner->>Dispatch: Describe stuck symptom
  Dispatch->>Dispatch: Map symptom to technique
  Dispatch-->>Practitioner: Recommend specific skill
  Practitioner->>Technique: Apply process (steps/examples)
  alt Resolved
    Technique-->>Output: Document insights/actions
    Output-->>Practitioner: Next steps
  else Still stuck
    Technique-->>Dispatch: Feedback: unresolved
    Dispatch-->>Practitioner: Suggest alternative/combined technique
  end
Loading

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~12 minutes

Poem

A hare with notes and nimble paws,
I mapped the maze of thinking laws.
New trails for scale and pattern sight,
When stuck, I route the quickest right.
I tuck tensions where they thrive—
Then hop to trace what ideas survive. 🐇✨

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)
Check name Status Explanation Resolution
Title Check ⚠️ Warning The title only highlights the addition of problem-solving skills and omits other significant changes such as new architecture and research skills and updates to existing collaboration guides, so it does not fully represent the primary scope of the pull request. Please update the title to reflect all major additions and modifications, for example: “Add problem-solving, architecture, and research skills from amplifier patterns” or a similarly concise summary covering new skills and updated guides.
✅ Passed checks (2 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Docstring Coverage ✅ Passed No functions found in the changes. Docstring coverage check skipped.
✨ Finishing touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch amplifier-skills

Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (4)
skills/architecture/ABOUT.md (1)

7-8: Wrap the repository URL to satisfy markdownlint.

markdownlint (MD034) flags the bare URL on Line 7. Wrapping it in angle brackets resolves the warning while keeping the text identical.

-- URL: https://github.com/microsoft/amplifier
+- URL: <https://github.com/microsoft/amplifier>
skills/research/ABOUT.md (1)

7-8: Fix the bare URL to clear MD034.

Line 7 still has an unwrapped URL, so markdownlint continues to warn. Angle brackets silence the rule without altering meaning.

-- URL: https://github.com/microsoft/amplifier
+- URL: <https://github.com/microsoft/amplifier>
skills/collaboration/executing-plans/SKILL.md (1)

72-78: Remove the duplicated blocker reminder.

The new “Stop and Ask for Help” section already captures this guidance, yet Line 78 still repeats the old wording. Drop the duplicate to keep the Remember section focused.

 - Reference skills when plan says to
 - Between batches: just report and wait
-- Stop when blocked, don't guess
skills/problem-solving/ABOUT.md (1)

7-8: Convert the bare URL to comply with MD034.

Line 7 needs angle brackets so markdownlint stops flagging the link.

-- URL: https://github.com/microsoft/amplifier
+- URL: <https://github.com/microsoft/amplifier>
📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between dee324d and f801cd6.

📒 Files selected for processing (13)
  • skills/architecture/ABOUT.md (1 hunks)
  • skills/architecture/preserving-productive-tensions/SKILL.md (1 hunks)
  • skills/collaboration/brainstorming/SKILL.md (3 hunks)
  • skills/collaboration/executing-plans/SKILL.md (2 hunks)
  • skills/problem-solving/ABOUT.md (1 hunks)
  • skills/problem-solving/collision-zone-thinking/SKILL.md (1 hunks)
  • skills/problem-solving/inversion-exercise/SKILL.md (1 hunks)
  • skills/problem-solving/meta-pattern-recognition/SKILL.md (1 hunks)
  • skills/problem-solving/scale-game/SKILL.md (1 hunks)
  • skills/problem-solving/simplification-cascades/SKILL.md (1 hunks)
  • skills/problem-solving/when-stuck/SKILL.md (1 hunks)
  • skills/research/ABOUT.md (1 hunks)
  • skills/research/tracing-knowledge-lineages/SKILL.md (1 hunks)
🧰 Additional context used
🪛 markdownlint-cli2 (0.18.1)
skills/architecture/ABOUT.md

7-7: Bare URL used

(MD034, no-bare-urls)

skills/research/ABOUT.md

7-7: Bare URL used

(MD034, no-bare-urls)

skills/problem-solving/ABOUT.md

7-7: Bare URL used

(MD034, no-bare-urls)

@obra obra merged commit 7421ddf into main Oct 11, 2025
1 check passed
obra added a commit to obra/superpowers-marketplace that referenced this pull request Oct 11, 2025
Updated plugin source format to use URL instead of GitHub repo because the github repo format breaks for users without github ssh keys configured.

Fixes obra/superpowers#1
@obra obra deleted the amplifier-skills branch October 11, 2025 16:44
obra added a commit that referenced this pull request Oct 11, 2025
Documents all changes since v1.0.0:
- Skills repository separation (breaking change)
- New problem-solving and research skills (PR #1)
- Personal superpowers system (PR #2, later replaced)
- Auto-update functionality
- Skills improvements (using-skills v4.0.0, sharing-skills v2.0.0)
- Tools improvements (find-skills, skill-run)
- Plugin infrastructure changes
- Migration guide for existing users
@coderabbitai coderabbitai bot mentioned this pull request Oct 11, 2025
9 tasks
EthanJStark pushed a commit to EthanJStark/superpowers that referenced this pull request Dec 16, 2025
Add problem-solving skills from amplifier patterns
EthanJStark pushed a commit to EthanJStark/superpowers that referenced this pull request Dec 16, 2025
Documents all changes since v1.0.0:
- Skills repository separation (breaking change)
- New problem-solving and research skills (PR obra#1)
- Personal superpowers system (PR obra#2, later replaced)
- Auto-update functionality
- Skills improvements (using-skills v4.0.0, sharing-skills v2.0.0)
- Tools improvements (find-skills, skill-run)
- Plugin infrastructure changes
- Migration guide for existing users
risk-free-value pushed a commit to risk-free-value/superpowers-beads that referenced this pull request Dec 19, 2025
New epic (Superpowers-hfa) with 5 tasks:
- TDD skill: revert discard→delete with Rule obra#1 compliance
- writing-skills: add 'ask first' to No exceptions blocks
- writing-skills: add test artifact cleanup step
- testing-skills-with-subagents: add 'ask first'
- Verification: grep checks for compliance

Also reorganize plan files into bead_plans/ subdirectory.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
risk-free-value pushed a commit to risk-free-value/superpowers-beads that referenced this pull request Dec 19, 2025
- Change all "Discard" to "Delete" (lines 37, 43, 244, 278, 301)
- Remove stash escape hatch that defeated TDD's cognitive purpose
- Add modified/new file distinction for Rule obra#1 compliance:
  - Modified files: git checkout (safe, no permission needed)
  - New files: ask permission before deleting
- Update summary with modified/new clarification

Closes Superpowers-n8s

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
risk-free-value pushed a commit to risk-free-value/superpowers-beads that referenced this pull request Dec 19, 2025
- writing-skills: add 'Ask your human partner before deleting' to Iron
  Law and Good example, update Red Flags summary
- writing-skills: add test artifact cleanup step to Deployment checklist
- testing-skills-with-subagents: add 'ask first' to After example

Completes CLAUDE.md Rule obra#1 compliance for delete language.
Closes Superpowers-hfa epic.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
risk-free-value pushed a commit to risk-free-value/superpowers-beads that referenced this pull request Dec 19, 2025
Adds 12 granular beads to track the removal of writing-plans and
using-git-worktrees skills, structured for TDD execution:

Phase 1 - Verification:
- Superpowers-sht: Verify replacement skills exist

Phase 2 - Pre-deletion updates:
- Superpowers-hpm: Rename command write-plan → plan-to-beads
- Superpowers-xz2: Update brainstorming skill
- Superpowers-lts: Update finishing-a-development-branch skill
- Superpowers-jlx/u70/ctj/9wt: Update README (4 changes)

Phase 3 - Approval:
- Superpowers-dnk: Human approval checkpoint (CLAUDE.md Rule obra#1)

Phase 4 - Deletion (requires approval):
- Superpowers-8wb: Delete skills/writing-plans/
- Superpowers-v5d: Delete skills/using-git-worktrees/

Phase 5 - Validation:
- Superpowers-urp: Post-deletion validation and commit

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants