CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

repo-scan

Bootstrap pointer that installs the external repo-scan skill from a pinned, reviewable commit. Use when repo-scan must be installed before running its cross-stack source-code asset audit; this ECC pointer does not perform the audit itself.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/repo-scan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%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.

The body's operational core is strong: a robust, executable install workflow with real validation and rollback. Its weaknesses are token bloat — an inlined 100-line defensive script plus capability/depth/example sections that duplicate the installed skill's docs — and the absence of any bundle structure to offload that material.

Suggestions

Move the ~100-line install script into scripts/install.sh and reduce the body to the one-line invocation plus a note on what the script does (pinning, confirmation, rollback); this fixes both conciseness and progressive disclosure.

Trim or collapse the Core Capabilities, Analysis Depth Levels, Examples, and Best Practices sections to a few routing-relevant lines — the installed skill's own SKILL.md will restate these after installation, so the pointer pays for them twice.

Make the post-install step concrete: specify how to reload the harness (e.g. restart the session or /skills reload) and what invoking repo-scan looks like, instead of the vague "Reload your agent harness, then invoke repo-scan again".

DimensionReasoningScore

Conciseness

The ~100-line inline install script (mv -T probing, lock files, backup/rollback machinery) plus the Core Capabilities, Analysis Depth Levels, How It Works, Examples, and Best Practices sections largely duplicate the installed skill's own documentation, producing several padded sections that compete for context tokens — noticeably verbose rather than merely tightenable.

2 / 5

Actionability

The installation block is fully executable, copy-paste-ready bash with a pinned commit hash, a staged source path to review, and a typed confirmation prompt; minor gaps remain, such as "Reload your agent harness" giving no concrete command and the review step lacking a suggested inspection command.

4 / 5

Workflow Clarity

The sequence is explicit with genuine validation checkpoints: clone to a detached pinned commit, review before approving, typed `install` confirmation before any destructive replacement, a lock against concurrent installs, backup-and-rollback with error messages on every failure path, and a re-invoke step after install — matching the explicit-validation-with-feedback-loops anchor.

5 / 5

Progressive Disclosure

No bundle files exist, and while section organization is good, the 100-line install script is exactly the content that belongs in a separate scripts/ file (e.g. scripts/install.sh) and is fully inlined — fitting the some-structure-but-should-be-separate-content-inline anchor.

3 / 5

Total

14

/

20

Passed

Description

66%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.

The description is honest and distinctive: it clearly scopes itself as an installer bootstrap rather than the audit tool. Its weaknesses are a circular when-clause that depends on already knowing the skill name and missing natural trigger phrases for the underlying audit need.

Suggestions

Replace the circular trigger with situational phrases, e.g. "Use when the user wants a repo-scan audit (legacy codebase takeover, third-party/vendored code audit, monorepo refactoring inventory) and the skill is not yet installed".

Add one or two natural synonyms users would say, such as "vendored dependencies", "source-code audit", or "cross-stack codebase inventory", to improve trigger matching beyond the bare skill name.

Optionally name the supported stacks (C++, Android, iOS, Web) in the description so the capability scope is visible before installation.

DimensionReasoningScore

Specificity

"installs the external repo-scan skill from a pinned, reviewable commit" names the domain and one concrete action, but coverage stops at installation; it does not list several specific actions, so it falls between the 1-2-action anchor and the several-actions anchor, closer to the former's comprehensiveness limit.

3 / 5

Completeness

Both what ("installs the external repo-scan skill from a pinned, reviewable commit... does not perform the audit itself") and when ("Use when repo-scan must be installed before running its cross-stack source-code asset audit") are present, but the when-clause is circular — it restates the skill name rather than giving concrete situational triggers, so it does not reach the explicit-trigger-phrases anchor.

4 / 5

Trigger Term Quality

Terms like "repo-scan", "cross-stack source-code asset audit", and "pinned, reviewable commit" are relevant, but the natural phrases a user would say when they need the capability ("legacy codebase", "third-party code", "monorepo audit") are missing, matching the some-keywords-but-missing-variants anchor.

3 / 5

Distinctiveness Conflict Risk

The description targets one named skill and explicitly disclaims the audit itself ("this ECC pointer does not perform the audit itself"), giving it a clear niche with minimal risk of triggering for the wrong skill.

5 / 5

Total

15

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

affaan-m/ECC

Path

skills/repo-scan/SKILL.md

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.