CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-doctor

Use when the user wants their agent setup graded from real conversation history, asks which installed skills are actually working, or wants evidence-backed skill edits — scores recent local Claude Code / Codex sessions against efficiency and code-quality rubrics, then drafts skill changes gated by a deterministic aggregator and renders one local shareable report.

76

Quality

96%

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

The canonical home for this skill is skill-doctor in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 a tight, highly actionable five-step workflow with strong validation gates and feedback loops. Its one real weakness is progressive disclosure: the references and scripts it points to are not present in the bundle, so the well-signaled links resolve to nothing.

Suggestions

Ship the referenced bundle (scorers/efficiency.md, scorers/code-quality.md, references/*.md, assets/*.example.json, scripts/*.py) so the clearly-signaled links actually resolve.

If any referenced file is intentionally omitted in a minimal distribution, mark it as such inline rather than presenting a dead link as available.

Consider a one-line inventory note near the references section stating which files are required for the skill to run vs. optional reading material.

DimensionReasoningScore

Conciseness

Lean and efficient: numbered steps with concrete commands, a hard-rules list, a scripts table, and a references list, with no padding or explanation of concepts Claude already knows; the one editorial blockquote ("Privacy is the contract") is brief and load-bearing.

5 / 5

Actionability

Fully concrete and copy-paste ready — `mktemp -d`, `python scripts/collect_sessions.py --out "$RUN"`, the full aggregator invocation with flags, an exit-code table, and example asset paths cover the common cases.

5 / 5

Workflow Clarity

A clearly sequenced 1–5 pipeline with explicit validation checkpoints: stop when `sessions_sampled` is 0, labels validated against rubric tables, "Exit 4 is a stop: fix what it names and re-run", and a feedback loop, plus a Hard Rules checklist.

5 / 5

Progressive Disclosure

Structurally the overview is well-organized with clearly signaled one-level-deep references (scorers/, references/, assets/), but the referenced bundle files do not exist in ./references, ./scripts, ./assets, or ./scorers — every link is dangling, so against the actual bundle structure the navigation promise fails.

3 / 5

Total

18

/

20

Passed

Description

100%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 exemplary: third-person voice, explicit "Use when" triggers covering three natural user requests, multiple concrete actions, and a clearly delineated niche. It concisely answers what, when, and how it differs from adjacent skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "scores recent local Claude Code / Codex sessions against efficiency and code-quality rubrics", "drafts skill changes gated by a deterministic aggregator", "renders one local shareable report" — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what (scores sessions, drafts gated skill changes, renders a report) and when ("Use when the user wants…", "asks which…", "wants evidence-backed skill edits") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrasings like "wants their agent setup graded", "asks which installed skills are actually working", and "wants evidence-backed skill edits" cover the realistic ways a user would request this, with synonyms (graded/scored, working, edits).

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — grading an agent setup from real local session history — with distinct triggers and an explicit distinct_from note separating it from skillopt-sleep, write-a-skill, and self-eval, so conflict risk is minimal.

5 / 5

Total

20

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 8 missing

Warning

referenced_paths_exist

Referenced path issues: 20 missing

Warning

Total

13

/

16

Passed

Repository
alirezarezvani/claude-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.