CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

resolve-review-feedback

Address GitHub PR review feedback at line, file, and PR level — fetch, evaluate, fix, commit, and resolve. Use when given a PR URL, a review-comment URL, or a PR-level comment URL. Triggers: GitHub discussion URLs, "fix this review comment", "address PR feedback", "resolve PR comments", PR URLs with #discussion_, #issuecomment-, or #pullrequestreview- fragments.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

45%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 maximally lean but hollow wrapper: it delegates 100% of the skill's substance to an external shared-skill file that is not present in this bundle or environment. While token-efficient and unambiguous as a redirect, it provides no executable guidance, no workflow, and no resolvable reference on its own.

Suggestions

Inline or summarize the core workflow (fetch comments → evaluate → fix → commit → resolve threads) with explicit validation checkpoints instead of delegating entirely to the external file.

Ship the shared skill content inside the bundle (e.g., references/shared-skill.md with a relative link) so the reference resolves wherever the skill is installed; the current ~/.agents/skills/... path does not exist in this environment.

Add a one-line overview of what the skill does and how the shared file is organized so the body acts as an orienting pointer rather than a bare redirect.

DimensionReasoningScore

Conciseness

The body is two lines plus a provenance comment ("Generated by scripts/agent-harnesses.py; do not edit directly.") — no padding, no concepts explained, every token earning its place. Not 4: there is no over-explanation to trim; the comment serves a real purpose for a generated file.

5 / 5

Actionability

"Load and follow the shared skill at ~/.agents/skills/resolve-review-feedback/SKILL.md" is a concrete directive but provides zero task-level guidance — no commands or steps for fetching comments, fixing code, committing, or resolving threads, and the referenced path does not exist in this environment. Not 3: the body contains no partial task guidance to be incomplete; not 1: the single directive is concrete (a specific path), not vague.

2 / 5

Workflow Clarity

The multi-step workflow the description promises ("fetch, evaluate, fix, commit, and resolve") is entirely absent from the body — no sequence, no steps, no validation checkpoints for commit/resolve operations. The simple-skill exception does not apply since this is a multi-step task; not 2 because there is not even a rough sequence present, only a redirect.

1 / 5

Progressive Disclosure

A single, clearly signaled, one-level reference is present, but the body offers no overview or navigation structure, and the reference points outside the bundle to a path that does not resolve here. Not 4: a bare pointer with no overview content and a dangling external path is more than a 'minor organization gap'; not 2: nothing is inlined and the reference is not buried.

3 / 5

Total

11

/

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: it states concrete capabilities at all three feedback levels, gives an explicit 'Use when' clause with quoted natural trigger phrases and URL-fragment patterns, and occupies a distinct niche. It matches the rubric's good_overall_examples pattern precisely.

DimensionReasoningScore

Specificity

"Address GitHub PR review feedback at line, file, and PR level — fetch, evaluate, fix, commit, and resolve" lists five concrete actions across three explicit scope levels, comprehensively covering the workflow. Not 4: coverage of fetch→evaluate→fix→commit→resolve leaves no minor gaps in capability description.

5 / 5

Completeness

Explicitly answers what ("fetch, evaluate, fix, commit, and resolve" at "line, file, and PR level") and when ("Use when given a PR URL, a review-comment URL, or a PR-level comment URL. Triggers: ...") with concrete trigger phrases. Not 4: the 'when' clause is fully explicit, not merely adequate.

5 / 5

Trigger Term Quality

Includes natural quoted phrases users would say ("fix this review comment", "address PR feedback", "resolve PR comments") plus URL-fragment triggers (#discussion_, #issuecomment-, #pullrequestreview-) that serve as the domain's file-extension equivalents, with fix/address/resolve synonyms covered. Not 4: the trigger set exceeds 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche — resolving GitHub PR review feedback — with distinct triggers (review-comment URLs, #pullrequestreview- fragments) unlikely to fire for adjacent skills like general code review or PR creation. Not 4: the trigger set is tightly scoped with minimal, not minor, overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

phatblat/dotfiles

Path

.claude/skills/resolve-review-feedback/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.