CtrlK
BlogDocsLog inGet started
Tessl Logo

commit-archaeologist

Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks "why does this code exist", "who wrote this function and why", or to "explain the history of this function" before a rewrite, refactor, or risky edit. Runs entirely locally.

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, well-structured instruction skill: executable commands for both usage modes, explicit error-handling checkpoints, a defined report format, and correct deferral of interpretation detail to a real one-level-deep reference. The only weakness is minor redundancy between the intro, the frontmatter description, and the trailing file index.

DimensionReasoningScore

Conciseness

The body never teaches git concepts Claude already knows and every section carries skill-specific rules, so it is well above anchor 3. It is 4 rather than 5 because the opening paragraph restates the frontmatter description and the trailing "Files" section re-lists both bundle paths already cited inline — minor trimmable redundancy, matching "minor instances of over-explanation that could be trimmed".

4 / 5

Actionability

Copy-paste-ready commands cover both modes — "python3 scripts/archaeologist.py /path/to/repo src/cache.py --lines 40-72 --json" and the file-history variant with "omit --lines" — plus a glossed JSON field list and a concrete six-part report format. Specific commands and examples cover the common cases fully, matching the 5 anchor.

5 / 5

Workflow Clarity

A clear gather-target → run-dig → read-reference → read-JSON → write-report → follow-ups sequence with explicit checkpoints and error feedback: "If either path is missing, ask only for the missing value" and "If it rejects a path or range, report that error and ask for a corrected target". The skill is read-only, so the destructive-operation validation cap does not apply; this matches the 5 anchor's explicit validation and error-recovery steps.

5 / 5

Progressive Disclosure

The body is an overview that defers interpretation detail to a single, clearly signaled, one-level-deep reference ("Before interpreting the JSON, read references/reading-git-history.md"), and both referenced bundle files exist and are substantive. Content is appropriately split across SKILL.md, the reference guide, and the script, matching the 5 anchor exactly.

5 / 5

Total

19

/

20

Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly states what the skill does, when to use it with natural quoted trigger phrases, and a distinguishing local-only constraint. The main gaps are missing common trigger synonyms (git blame, when-was-this-added phrasings) and slight overlap with plain blame and refactor-time queries.

Suggestions

Add one or two common trigger phrasings users actually say, e.g. "who last touched this line", "when was this added", or "git history of this file", to broaden natural-term coverage.

Sharpen the boundary against plain blame output (e.g. "for the reasoning behind the code, not just blame output") so a user who only wants git blame output does not trigger this skill.

DimensionReasoningScore

Specificity

"Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent" names the domain plus five concrete capabilities in third person. It lists multiple specific concrete actions with comprehensive coverage of the skill's outputs, matching the 5 anchor rather than 4, which requires minor gaps.

5 / 5

Completeness

The first sentence explicitly answers "what" and the second gives an explicit "Use when" clause with three concrete quoted trigger phrases and an editing context. This matches the 5 anchor (both what and when with concrete triggers), not 4, whose "when" is merely serviceable.

5 / 5

Trigger Term Quality

Quoted phrases "why does this code exist", "who wrote this function and why", and "explain the history of this function" are exactly what users naturally say, plus "before a rewrite, refactor, or risky edit". It falls short of 5 because common variations such as "git blame", "when was this line added", or "git history of this file" are missing.

4 / 5

Distinctiveness Conflict Risk

"Why does this code exist" and "explain the history of this function" carve a clear niche with minimal conflict, and "Runs entirely locally" further separates it. It sits at 4 rather than 5 because "who wrote this function and why" overlaps a plain git-blame request and "before a rewrite, refactor" brushes against refactor/review skills — minor overlap with closely related skills.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Shubhamsaboo/awesome-llm-apps
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.