Workflow Skill Extractor Report — 2026-02-22

[github-actions[bot]]

This report summarizes an automated analysis of 158 workflow files in .github/workflows/ to identify reusable skills and shared component opportunities. The analysis reviewed 56 existing shared components before identifying new candidates.

3 actionable GitHub issues have been created from the top-priority findings.

Key Statistics

Metric	Value
Total workflows analyzed	158
Existing shared components	56
New skills identified	8+
High-priority recommendations	3
Estimated lines saved (top 3)	~320–470 lines

---

Workflows Analyzed

A representative sample of 20+ workflows was examined in detail, including: sergo, typist, semantic-function-refactor, daily-file-diet, glossary-maintainer, go-fan, daily-compiler-quality, repository-quality-improver, archie, duplicate-code-detector, copilot-pr-nlp-analysis, copilot-pr-prompt-analysis, copilot-agent-analysis, org-health-report, daily-code-metrics, static-analysis-report, terminal-stylist, q, go-logger, mcp-inspector.

Existing Shared Components (Already in Use)

The most heavily imported components are:

Component	Import Count
shared/reporting.md	80
shared/jqschema.md	20
shared/python-dataviz.md	7
shared/trending-charts-simple.md	6
shared/gh.md	6
shared/trends.md	5
shared/copilot-pr-data-fetch.md	4
shared/go-make.md	3

---

🔍 Identified Skills

High Priority Skills

1. Serena Go Analysis Tool Configuration

• Frequency: 16 workflows use serena: ["go"] with zero existing shared component
• Size: ~10–15 lines of repeated tool config per workflow
• Priority: 🔴 High
• Description: Standard frontmatter tool block for Go code analysis with the Serena MCP server. Includes serena: ["go"], edit:, common bash: allowlists for Go file discovery, and a markdown body with project activation guidance.
• Workflows: archie, cloclo, daily-compiler-quality, daily-file-diet, daily-testify-uber-super-expert, developer-docs-consolidator, duplicate-code-detector, glossary-maintainer, go-fan, mcp-inspector, q, repository-quality-improver, semantic-function-refactor, sergo, terminal-stylist, typist
• Recommendation: Create shared/mcp/serena-go.md

2. Go Code Analysis Constraints (Prompt Skill)

• Frequency: 5+ workflows with near-identical "Important Constraints" and Serena activation blocks
• Size: ~20–30 lines of repeated prompt text per workflow
• Priority: 🔴 High
• Description: Prompt skill with standardized Go analysis guidelines: file exclusion constraints, pkg/ directory focus, Serena project activation steps, and common bash discovery commands.
• Workflows: typist, semantic-function-refactor, duplicate-code-detector, daily-file-diet, sergo
• Recommendation: Create shared/go-analysis-constraints.md

3. Copilot PR Analysis Base Setup

• Frequency: 4 workflows with near-identical import chains and tool configurations
• Size: ~15–20 lines of repeated imports and tool config per workflow
• Priority: 🟡 Medium
• Description: Combined setup that bundles copilot-pr-data-fetch + jqschema + reporting imports with standard tool configuration (github: toolsets: [default], edit:, bash: ["*"]) and guidance on repo-memory naming conventions.
• Workflows: copilot-pr-nlp-analysis, copilot-pr-prompt-analysis, copilot-agent-analysis, copilot-pr-merged-report
• Recommendation: Create shared/copilot-pr-analysis-base.md

Medium Priority Skills

4. Daily Tracker-ID Discussion Pattern

• Frequency: 53 workflows use close-older-discussions: true with expires: 1d, max: 1
• Description: Standard daily idempotent discussion configuration. Cannot be extracted via imports: (frontmatter-only config), but could be addressed by a workflow template or generator.
• Priority: 🟡 Medium (non-trivial to extract)

5. repo-memory Historical Tracking Setup

• Frequency: 21 workflows use repo-memory with very similar configs (all use max-file-size: 102400, JSON/JSONL/CSV/MD globs)
• Description: A prompt skill explaining repo-memory best practices, naming conventions, and file structure could standardize how workflows initialize and use historical tracking.
• Priority: 🟡 Medium

Low Priority Skills

6. agentic-workflows + GitHub Toolsets Pattern

• 26 workflows use agentic-workflows: with slight variations in toolsets
• Low extraction value — configs vary by workflow purpose

7. Docker Static Analysis Tool Setup

• static-analysis-report.md has a reusable Docker image pull + verify pattern
• Only 1-2 workflows currently use it

8. Python Data Visualization + Trending

• python-dataviz.md + trending-charts-simple.md are already shared but often imported together — a composite "analytics" shared component could bundle these

---

💡 Detailed Recommendations

Recommendation 1: shared/mcp/serena-go.md

Full Details

Current State (example from typist.md and semantic-function-refactor.md):

tools:
  serena: ["go"]
  github:
    toolsets: [default]
  edit:
  bash:
    - "find pkg -name '*.go' ! -name '*_test.go' -type f"
    - "find pkg -type f -name '*.go' ! -name '*_test.go'"
    - "find pkg/ -maxdepth 1 -ls"
    - "wc -l pkg/**/*.go"
    - "cat pkg/**/*.go"
    - "grep -r 'func ' pkg --include='*.go'"

This exact block (with minor variations) is duplicated across 16 workflows.

Proposed Shared Component:

---
tools:
  serena: ["go"]
  edit:
  bash:
    - "find pkg -name '*.go' ! -name '*_test.go' -type f"
    - "find pkg -type f -name '*.go' ! -name '*_test.go'"
    - "find pkg/ -maxdepth 1 -ls"
    - "wc -l pkg/**/*.go"
    - "cat pkg/**/*.go"
    - "head -n * pkg/**/*.go"
    - "grep -r 'func ' pkg --include='*.go'"
---

## Serena Go Code Analysis

The Serena MCP server is configured for Go semantic code analysis.
...

Migration Path:

1. Create shared/mcp/serena-go.md
2. For each of the 16 workflows, add - shared/mcp/serena-go.md to imports: and remove the duplicated tool config lines
3. Workflows needing additional toolsets (e.g., github: toolsets: [default, issues]) keep those inline
4. Run make recompile

Impact:

• Lines saved: ~160–240 (10-15 per workflow × 16 workflows)
• Maintenance: Serena config changes require 1 file edit instead of 16

Recommendation 2: shared/copilot-pr-analysis-base.md

Full Details

Current State: Three workflows import the same 3 files and configure nearly identical tools:

# All three workflows have:
imports:
  - shared/jqschema.md
  - shared/reporting.md
  - shared/copilot-pr-data-fetch.md
tools:
  repo-memory:
    branch-name: memory/(name)
    description: "Historical (description)"
    file-glob: ["memory/(name)/*.json", "memory/(name)/*.jsonl",
                "memory/(name)/*.csv", "memory/(name)/*.md"]
    max-file-size: 102400
  edit:
  github:
    toolsets: [default]
  bash: ["*"]

Proposed Shared Component:

---
tools:
  github:
    toolsets: [default]
  edit:
  bash: ["*"]
imports:
  - shared/jqschema.md
  - shared/reporting.md
  - shared/copilot-pr-data-fetch.md
---

Workflow-specific repo-memory stays inline since branch names must differ per workflow.

Migration Path:

1. Create shared/copilot-pr-analysis-base.md
2. Replace 3-import chain in each of 4 workflows with single import
3. Run make recompile

Recommendation 3: shared/go-analysis-constraints.md

Full Details

Current State: 5 workflows contain this text (near-verbatim):

## Important Constraints

1. **Only analyze `.go` files** - Ignore all other file types
2. **Skip test files** - Never analyze files ending in `_test.go`
3. **Focus on pkg/ directory** - Primary analysis area
4. **Use Serena for semantic analysis** - Leverage the MCP server's capabilities

Plus each has a Serena activation block (5–10 lines each).

Proposed Shared Component:
A pure prompt skill (---\n--- frontmatter) with the canonical constraints text, Serena activation guide, and common bash discovery examples.

Migration Path:

1. Create shared/go-analysis-constraints.md
2. Add import to 5 workflows
3. Remove duplicated constraint text from each workflow
4. Run make recompile

---

📈 Impact Analysis

By Category

Category	Skills Found	Est. Lines Saved
Tool Configurations	3 (serena-go, copilot-pr, agentic-wf)	~200–300
Prompt Skills	2 (go-constraints, repo-memory guide)	~120–200
Data Processing	1 (pr-analysis-base)	~60–80
Setup Steps	2 (docker tools, py+trending)	~40–80

By Priority

Priority	Skills	Est. Lines Saved	Workflows Affected
🔴 High	2	~260–390	16–21
🟡 Medium	4	~120–200	8–15
⚪ Low	2+	~40–80	2–4

---

✅ Created Issues

This analysis created 3 actionable GitHub issues:

1. [refactoring] Extract Serena Go Analysis Tool Configuration into shared component — 16 workflows, ~160–240 lines saved
2. [refactoring] Extract Copilot PR Analysis Base Setup into shared component — 4 workflows, ~60–80 lines saved
3. [refactoring] Extract Go Code Analysis Constraints into shared prompt skill — 5 workflows, ~100–150 lines saved

---

🎯 Next Steps

1. Review and prioritize the 3 created issues
2. Start with shared/mcp/serena-go.md — highest impact (16 workflows), clean extraction
3. Then tackle shared/go-analysis-constraints.md — pure prompt skill, low risk
4. Then tackle shared/copilot-pr-analysis-base.md — consolidates 4 similar workflows
5. Consider a medium-priority initiative for repo-memory usage guidelines
6. Schedule a follow-up extractor run in ~1 month after implementation

---

📚 Methodology

• Analyzed all 158 workflow files in .github/workflows/
• Reviewed all 56 existing shared components to avoid duplicating what already exists
• Examined tool configurations, import patterns, and prompt text across a 20+ workflow sample
• Quantified frequency by counting exact patterns via grep across the full workflow set
• Prioritized based on: frequency × lines saved × ease of extraction

Analysis Date: 2026-02-22
Analyzer: Workflow Skill Extractor v1.0
Workflow Run: §22280625020

References:

• Workflow run §22280625020

AI generated by Workflow Skill Extractor

• expires on Mar 1, 2026, 4:19 PM UTC