CtrlK
BlogDocsLog inGet started
Tessl Logo

bug-fixing

Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.

70

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 deliberately minimal overview that delegates everything to a single well-placed reference file — excellent token efficiency and structure. The trade-off is that the body alone gives no workflow summary or verification commands, so actionability depends entirely on opening the reference.

Suggestions

Add a one-line inline summary of the core workflow (reproduce → root-cause → patch → regression test → focused verification) so the skill is actionable before opening the reference.

Inline the key verification commands (e.g., `pnpm --filter @composio/<package> test` and `pytest tests/test_<feature>.py`) as a quick-start block.

Convert the reference path into a markdown link (e.g., [regression-testing.md](references/regression-testing.md)) to make the navigation signal explicit.

DimensionReasoningScore

Conciseness

The body is three lean lines — "Use this skill for defect work" and a single pointer to the reference — with zero padding and no explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

"Read `references/regression-testing.md` before editing code" is a concrete, executable instruction to a real file, but the body itself contains no commands, code, or workflow summary — all specifics are deferred to the reference.

3 / 5

Workflow Clarity

The referenced file lays out a clear 5-step sequence (reproduce → trace root cause → patch → add regression test → run focused then broader checks) with a verification checkpoint, but the body surfaces none of it and there is no error-recovery loop.

4 / 5

Progressive Disclosure

The bundle is correctly structured: SKILL.md is a minimal overview and `references/regression-testing.md` is a real, well-signaled, one-level-deep reference that holds the detail — appropriate split with easy navigation.

5 / 5

Total

17

/

20

Passed

Description

92%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: concrete third-person actions, explicit trigger conditions with concrete phrases, and clear negative scope. Only minor gap is a few missing natural synonyms (e.g., error, crash) among trigger terms.

DimensionReasoningScore

Specificity

"Fix defects ... with focused reproduction, root-cause analysis, regression tests, and narrow verification" lists multiple specific concrete actions covering the full bug-fix workflow in third-person voice, matching the comprehensive anchor.

5 / 5

Completeness

It explicitly answers both "what" (fix defects via reproduction, root-cause analysis, regression tests, verification) and "when" ("Use when the user reports a bug, failing test, CI regression...") with concrete trigger phrases, plus negative scope guidance.

5 / 5

Trigger Term Quality

"bug, failing test, CI regression, runtime defect, incorrect SDK behavior" are natural phrases users would say, but common synonyms like "error", "crash", "broken", or "traceback" are missing — good coverage with a few natural terms absent.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (defect work in the Composio SDK repository) with distinct triggers and explicit exclusions ("Do not use for new feature design or broad refactors"), minimizing conflict with feature or refactor skills.

5 / 5

Total

19

/

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
ComposioHQ/composio
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.