CtrlK
BlogDocsLog inGet started
Tessl Logo

ghost-repo-context

Scans directory structure, detects projects, maps dependencies, and documents code organization into a repo.md file. Use when the user needs a codebase overview, project structure map, or repository context before security analysis.

92

3.57x
Quality

90%

Does it follow best practices?

Impact

100%

3.57x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

An exemplary instruction-only skill body: lean, fully executable, with a well-sequenced workflow that includes cache short-circuiting, per-project failure isolation, and a validate-and-retry checkpoint. The only weakness is reference resolution risk — the skill_dir find pattern ('repo-context') does not match the frontmatter name ('ghost-repo-context'), and no bundle files were provided to verify the referenced files exist.

Suggestions

Align the Setup discovery path with the skill's actual directory/frontmatter name (find '*/skills/ghost-repo-context/SKILL.md' or derive skill_dir from the loaded skill's own path) so detector.md, summarizer.md, and template-repo.md reliably resolve.

State explicitly what to do if <skill_dir>/detector.md or summarizer.md is missing (e.g., report an error) so the reference chain cannot fail silently.

DimensionReasoningScore

Conciseness

The ~55-line body contains zero concept explanations and no padding: every section (Inputs, Tool Restrictions, Setup, cache check, Workflow) carries operational information only. It assumes Claude's competence throughout, e.g. the one-line cache_dir derivation and the terse step descriptions — every token earns its place.

5 / 5

Actionability

Both bash blocks are copy-paste ready, inputs are enumerated as concrete key=value pairs, the exact output string ("Repository context is at: <cache_dir>/repo.md") is given, and every edge case is handled explicitly: cache hit short-circuit, no projects detected, per-project summarization failure, and one-retry on malformed output. Guidance is fully executable with no gaps.

5 / 5

Workflow Clarity

Five clearly sequenced steps with a cache-first short-circuit, explicit data flow between steps (detection output feeding summarizer inputs), and a genuine feedback loop: step 4 reads repo.md back, verifies expected sections from the template, and retries the write once before reporting an error. Sequence, checkpoints, and error recovery are all explicit.

5 / 5

Progressive Disclosure

The body is a clean overview with well-signaled, one-level-deep references to detector.md, summarizer.md, and template-repo.md, each tied to a specific workflow step. However, no bundle files exist to verify these references resolve, and the Setup find targets '*/skills/repo-context/SKILL.md' while the frontmatter name is 'ghost-repo-context' — a path mismatch that could break reference resolution, leaving a minor navigation gap below anchor 5.

4 / 5

Total

19

/

20

Passed

Description

83%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, well-structured description that explicitly answers both what the skill does and when to use it, with a concrete deliverable (repo.md) and a distinctive security-analysis framing. Trigger coverage is good but misses common synonyms, and one action phrase ("scans directory structure") is slightly generic.

Suggestions

Replace the generic "Scans directory structure" with a more concrete action (e.g., "enumerates directories and dependency manifests") so all four verbs are equally specific.

Add natural trigger variations users would say, such as "understand a codebase", "map this repository", or "get repo context", to broaden trigger-term coverage.

Sharpen distinctiveness by emphasizing the output artifact earlier (e.g., "Builds a repo.md context file...") to reduce overlap with general codebase-exploration skills.

DimensionReasoningScore

Specificity

The description lists four concrete actions ("detects projects, maps dependencies, and documents code organization into a repo.md file") with a named output artifact, but "Scans directory structure" is comparatively generic, leaving minor gaps in coverage. This sits between the several-specific-actions anchor (4) and the comprehensive anchor (5), closer to 4 because one action lacks concreteness.

4 / 5

Completeness

Both parts are explicit: the 'what' is the four concrete actions with the repo.md deliverable, and the 'when' is a fully spelled-out "Use when the user needs..." clause with concrete trigger scenarios. This directly matches the anchor requiring both what AND when with concrete trigger phrases; the when-clause is explicit, not merely present.

5 / 5

Trigger Term Quality

"Use when the user needs a codebase overview, project structure map, or repository context before security analysis" provides good natural-phrase coverage that users would actually say. Common variations like "understand the codebase" or "map this repository" are missing, so it does not reach the comprehensive-synonym anchor (5).

4 / 5

Distinctiveness Conflict Risk

The repo.md output and "before security analysis" framing carve a clear niche, but "codebase overview" and "project structure map" are triggers that general codebase-exploration skills would also plausibly claim. Mostly distinct with minor overlap risk against closely related exploration skills — anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
ghostsecurity/skills
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.