CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-change

Review a proposed code change and its evidence when asked to assess implementation quality.

Quality

73%

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 ./internal/adaptertest/testdata/all-agents/want/codex/files/.codex/skills/acr__example__all-agents__review-change/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 is an extremely lean, single-step instruction with a concrete command and an explicit output contract, and the simple-skill exception keeps workflow clarity high. Weaknesses are minor but real: the script path does not match the bundle layout, failure handling is unspecified, and the bundled reference file is orphaned.

Suggestions

Reference the script by its bundle-relative path (scripts/check.sh) so the command resolves wherever the skill is installed.

Add one line of failure guidance, e.g. "If it exits non-zero, report the failure and stop" to close the validation feedback loop.

Either reference references/REFERENCE.md from the body or remove the orphaned file so the bundle structure matches the skill's navigation.

DimensionReasoningScore

Conciseness

The 8-line body is very lean and explains nothing Claude already knows, but "Process steps in order. Do not skip ahead." plus "Finish here." are redundant meta-statements for a single-step workflow that could be trimmed. This is anchor 4 (efficient with minor trimmable instances), not 5 (every token earning its place).

4 / 5

Actionability

"Run .codex/skills/acr__example__all-agents__review-change/scripts/check.sh" is a concrete command with an explicit output contract ("It emits {\"ok\":true} on stdout and exits non-zero on failure"), but the path does not match the bundle's actual scripts/check.sh location and no arguments or working directory are specified. Anchor 4 (mostly executable, minor gaps), not 5.

4 / 5

Workflow Clarity

The simple-skill exception applies: the single action (run the check script and read its result) is mostly unambiguous and the operation is non-destructive, so the validation cap does not apply. However, there is no instruction for what to do when the script exits non-zero, matching anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The body is short with a clear section, and the referenced script exists in the bundle, but it is referenced via a non-bundle-relative path instead of scripts/check.sh, and the bundled references/REFERENCE.md is never mentioned in the body. Minor organization gaps place this at anchor 4, not 5.

4 / 5

Total

16

/

20

Passed

Description

58%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 concise, in third person, and states a clear what plus an explicit when, but the what is a single composite action and the when-clause is self-referential rather than concrete trigger phrases. Trigger coverage misses common user phrasings like diff, PR, or pull request.

Suggestions

Add concrete trigger phrases to the when-clause, e.g. "Use when the user asks to review a PR, diff, or staged changes and their evidence."

Enumerate 2-3 concrete actions (e.g. "inspect the diff, run the check script, evaluate test evidence") to lift specificity and distinctiveness.

Include common synonyms users say naturally ("diff", "PR", "pull request") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Review a proposed code change and its evidence" names the code-review domain and one composite action, but does not list several concrete actions (no mention of inspecting diffs, running checks, or evaluating evidence types). It fits anchor 3 (domain plus 1-2 actions, not comprehensive), not 4 (several specific actions).

3 / 5

Completeness

Both parts are present: the what ("Review a proposed code change and its evidence") and an explicit when ("when asked to assess implementation quality"). The when-clause is somewhat circular and could be more concrete, matching anchor 4 rather than 5; the explicit when-clause means the missing-trigger cap of 3 does not apply.

4 / 5

Trigger Term Quality

Natural keywords like "review", "code change", and "assess implementation quality" are present, but common variations users would actually say ("diff", "PR", "pull request", "staged changes") are missing. This matches anchor 3 (relevant keywords, missing common variations), not 4 (good coverage with only a few missing).

3 / 5

Distinctiveness Conflict Risk

"Review a proposed code change" overlaps substantially with generic code-review skills, though "and its evidence" adds some distinctiveness. This sits at anchor 3 (somewhat specific but could still overlap with similar skills), not 4 (minor overlap risk only).

3 / 5

Total

13

/

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

jbaruch/agentic-context-registry

Path

internal/adaptertest/testdata/all-agents/want/codex/files/.codex/skills/acr__example__all-agents__review-change/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.