CtrlK
BlogDocsLog inGet started
Tessl Logo

review-fix-loop

Self-review a PR, fix all issues, and re-review in a loop until clean. Coordinates code-review, address-pr-comments, and fix-ci-tests skills.

54

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/review-fix-loop/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill excels at actionability and workflow clarity — every step has executable commands, clear gating logic, and robust validation with feedback loops. However, it is severely hampered by verbosity: the same GraphQL query appears three times verbatim, behavioral instructions are over-explained, and the document could be cut by 40-50% without losing any information. The monolithic structure would benefit from extracting repeated code into referenced scripts.

Suggestions

Extract the duplicated GraphQL unresolved-thread-counting query into a shared shell script (e.g., `count_unresolved_threads.sh`) and reference it from Steps 2E and 3, reducing ~60 lines of duplication.

Consolidate the behavioral rules (sections 3 'Never skip steps' and 4 'Execution continuity') into a single concise checklist of 3-4 bullet points instead of multi-paragraph explanations.

Move the security warning about prompt injection to a single brief note rather than repeating the 'do NOT read body fields' instruction four separate times throughout the document.

Consider extracting the Step 4 summary template and the Step 2A1 review request comment body into separate template files to reduce inline bulk.

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~400+ lines with massive duplication. The GraphQL pagination query for counting unresolved threads is repeated verbatim three times. The security warnings, gating checks, and execution continuity rules are over-explained. Many instructions (like 'never skip steps', 'never stall') are behavioral coaching that Claude doesn't need repeated at this length.

1 / 3

Actionability

The skill provides fully executable bash commands, specific GraphQL queries, exact CLI invocations for gh, git, and sub-skills. The code is copy-paste ready with concrete examples of commit message formats, PR comment bodies, and decision logic. Every step has clear, specific commands to run.

3 / 3

Workflow Clarity

The multi-step workflow is exceptionally well-sequenced with explicit gate checks between steps, a clear execution order diagram, validation checkpoints at every stage (2D verify push, 2E decision matrix, Step 3 verification), and feedback loops (loop back from 2E or Step 3 to Step 2). The SUCCESS_COUNT mechanism requiring 5 consecutive clean passes is a thorough validation approach.

3 / 3

Progressive Disclosure

The skill references sub-skills (code-review, address-pr-comments, fix-ci-tests) which provides some structural separation, but the main SKILL.md itself is monolithic with no bundle files to offload content to. The triplicated GraphQL query could be extracted to a shared script. The task creation list, execution order table, and detailed step descriptions are all inline in one massive document.

2 / 3

Total

9

/

12

Passed

Description

60%Scale 1-3

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 does a good job explaining the concrete workflow (self-review, fix, re-review loop) and naming the sub-skills it coordinates, which adds specificity. However, it lacks an explicit 'Use when...' clause, which caps completeness, and it could benefit from more natural trigger terms and clearer differentiation from the individual sub-skills it orchestrates.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to fully clean up a pull request, iterate on PR feedback until all issues are resolved, or run an end-to-end review-fix cycle.'

Include common user-facing trigger terms like 'pull request', 'iterate', 'review loop', 'clean up PR', and 'automated review' to improve discoverability.

Clarify how this skill differs from the individual code-review or address-pr-comments skills, e.g., 'Unlike individual review skills, this orchestrates the full cycle until no issues remain.'

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: self-review a PR, fix all issues, re-review in a loop, and names the coordinated sub-skills (code-review, address-pr-comments, fix-ci-tests).

3 / 3

Completeness

Clearly answers 'what' (self-review PR, fix issues, re-review in loop, coordinate sub-skills) but lacks an explicit 'Use when...' clause or trigger guidance for when Claude should select this skill.

2 / 3

Trigger Term Quality

Includes relevant terms like 'PR', 'review', 'fix', 'CI tests', and 'pr-comments', but misses common user variations like 'pull request', 'code review loop', 'iterate on PR', or 'clean up PR'. Coverage is partial.

2 / 3

Distinctiveness Conflict Risk

The description mentions coordinating code-review, address-pr-comments, and fix-ci-tests, which helps distinguish it as an orchestrator skill. However, it could overlap with any of those individual skills since it shares similar trigger terms like 'PR' and 'review'.

2 / 3

Total

9

/

12

Passed

Validation

90%

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

Validation — 10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
DataDog/rshell
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.