CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

flag-cleanup

Run the quarterly feature-flag cleanup workflow on the current repo

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 ./.gemini/skills/flag-cleanup/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 strong, lean body: concrete executable commands with parameterized defaults, clear usage examples, and explicit pre/post-conditions. The main weakness is the absence of validation checkpoints in the batch scan-audit-report workflow (e.g., verifying JSON output, handling empty results or scanner failure), which caps workflow clarity.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no explanations of what feature flags or git are; every section ("Usage", "Implementation", "Output", "Pre-conditions", "Post-conditions") earns its place, and the overview list doubles as a summary of Claude's non-scripted steps rather than padding. Not a 4 because no over-explanation or trimmable material was found.

5 / 5

Actionability

Concrete, copy-paste-ready commands with sensible parameter defaults are given ("python \"$SKILL/scripts/flag_debt_scanner.py\" --repo . --max-age-days \"${MAX_AGE_DAYS:-90}\" --format json > .flag-debt.json") plus concrete usage variants (--max-age-days, --flag-doc). Not a 5 because the hard-coded relative path "SKILL=engineering/feature-flags-architect/skills/feature-flags-architect" is fragile if the dependency is installed elsewhere, and the report-synthesis step is only described, not exemplified.

4 / 5

Workflow Clarity

The sequence is clear (numbered overview; labeled "Step 1/2/3" implementation; pre- and post-conditions), but this is a batch operation over many flags with no validation or verification checkpoints — no check that the JSON outputs are valid or non-empty, no handling for zero candidates or script failure — so workflow clarity is capped at 3 per the judging guidelines.

3 / 5

Progressive Disclosure

This is a simple, self-contained skill (~55 lines) with no bundle files and no need for external references; the single external dependency (the feature-flags-architect skill) is invoked by explicit path and flagged as a pre-condition, and sections are well-organized and easy to navigate, matching the simple-skill exception for a 5.

5 / 5

Total

17

/

20

Passed

Description

53%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 states a clear, niche 'what' but completely omits any 'when' guidance, so it would only be triggered by an explicit /flag-cleanup invocation rather than by natural user intent. It also undersells the skill's concrete capabilities (stale-flag scanning, kill-switch audit, removal planning, report generation) that the body clearly documents. Adding a trigger clause and naming the core actions would move it to the 4-5 range.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions feature flags, stale flags, flag cleanup/removal, or asks to audit feature-flag debt.'

Name the concrete capabilities in the description, e.g. 'Scans for stale feature flags, audits kill-switch documentation, and generates an owner-grouped removal plan and markdown report.'

Include natural synonyms users would say — 'stale flags', 'flag removal', 'toggles', 'flag debt' — to improve trigger-term coverage.

DimensionReasoningScore

Specificity

"Run the quarterly feature-flag cleanup workflow" names a concrete domain and a single concrete capability (feature-flag cleanup), matching the 'names domain and 1-2 concrete actions' anchor. It is not a 4 because the description lists none of the actual actions the body performs (scanning stale flags, auditing kill switches, generating removal plans).

3 / 5

Completeness

The 'what' is clear ("Run the quarterly feature-flag cleanup workflow on the current repo") but there is no 'Use when...' clause or equivalent trigger guidance, so per the judging guideline completeness is capped at 3; the word "quarterly" only weakly implies timing and does not tell Claude when to invoke it.

3 / 5

Trigger Term Quality

Relevant keywords like "feature-flag", "cleanup", and "quarterly" are present and would match a user saying 'clean up feature flags', but common variations such as 'stale flags', 'flag removal', 'toggles', or 'kill switches' are absent — the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"feature-flag cleanup" is a clear niche unlikely to trigger for unrelated skills, fitting 'mostly distinct; minor overlap risk' (e.g., with general code-cleanup or repo-hygiene skills). Not a 5 because the anchor's minimal-conflict examples include explicit distinct trigger phrases, which this description lacks entirely.

4 / 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

alirezarezvani/claude-skills

Path

.gemini/skills/flag-cleanup/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.