talk-stage2-research
Performs git archaeology, changelog analysis, and builds a verified factual timeline by cross-referencing git history with source material. REX mode only — skipped automatically in Concept mode. Use when building a REX talk and you need verified commit metrics, release timelines, and contributor data from a git repository.
66
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description that clearly defines specific capabilities and explicit trigger conditions. The 'REX mode only' constraint and detailed action list make it highly distinctive. The main weakness is that 'REX talk' is domain-specific jargon that limits discoverability for users unfamiliar with the term.
Suggestions
Consider briefly clarifying what a 'REX talk' is (e.g., 'retrospective/experience talk') so users unfamiliar with the term can still identify when this skill applies.
Add a few more natural trigger terms like 'git log', 'commit history', 'git blame', or 'project history analysis' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'git archaeology', 'changelog analysis', 'builds a verified factual timeline', 'cross-referencing git history with source material', 'verified commit metrics, release timelines, and contributor data'. | 3 / 3 |
Completeness | Clearly answers both what ('performs git archaeology, changelog analysis, builds verified factual timeline by cross-referencing git history') and when ('Use when building a REX talk and you need verified commit metrics, release timelines, and contributor data from a git repository'). | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'git', 'changelog', 'commit metrics', 'release timelines', 'contributor data', and 'git repository', but the term 'REX talk' is domain-specific jargon that many users might not naturally use. Missing common variations like 'git log', 'git blame', 'commit history'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically for REX mode talks requiring git-based factual verification. The 'REX mode only' constraint and specific use case (building a REX talk with verified git data) make it very unlikely to conflict with general git or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with clear executable commands, detailed output templates, and strong safety constraints (read-only git operations). Its main weakness is verbosity — the inline output templates consume significant tokens and could be externalized, and some introductory sections are redundant. The workflow is clear with good validation and anti-pattern guidance.
Suggestions
Move the three output format templates to a separate TEMPLATES.md file and reference it from the main skill to reduce token footprint
Remove or consolidate the 'When to Use This Skill' and 'What This Skill Does' sections — the header paragraph already covers this context
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary sections like 'When to Use This Skill' and 'What This Skill Does' that largely repeat the header description. The output format templates are quite verbose and could be more concise, though they do serve as actionable templates. The 'Tips' section adds marginal value. | 2 / 3 |
Actionability | Provides fully executable git commands with proper parameterization, complete output file templates with table structures, explicit input/output file paths, and a clear validation checklist. Everything is copy-paste ready and specific. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (read summary → git archaeology → changelog analysis → cross-reference → build timeline → write 3 files). Includes explicit validation checklist with safety constraints (read-only only), cross-reference verification steps, and anti-patterns that serve as error prevention. The 'Verify before asserting' and conflict-flagging rules provide feedback loops. | 3 / 3 |
Progressive Disclosure | References to related stages are well-signaled with relative links. However, the output format templates are very long and inline — these could be split into a separate TEMPLATES.md or similar file. The skill is ~150 lines when it could be more compact with external template references. No bundle files exist to offload this content to. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
60a4372
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.