CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr-post-review-findings

Post findings from the most recent review output as inline GitHub PR comments and record them in today's daily note. Use when invoked as `$pr-post-review-findings` or when the user asks to post review findings to the current PR.

Quality

86%

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

81%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 high-quality operational skill: the workflow is fully sequenced with validation checkpoints, error-recovery fallbacks, and a final verification step, and the commands are specific and nearly copy-paste ready. The only weaknesses are a small placeholder gap in the `gh api` call, slight redundancy between the entry-format example and its restated rules, and a daily-note format spec that could be split into a reference file.

DimensionReasoningScore

Conciseness

The body is dense with operational knowledge Claude cannot infer (the harness bash guard scanning inline JSON, the daily-note entry format, append rules), so nearly every token earns its place. Minor trimming is possible — the bullet formatting rules partially restate the markdown example above them — which keeps it at "efficient with minor instances of over-explanation" rather than lean anchor 5.

4 / 5

Actionability

Guidance is almost fully executable: exact `gh` commands with `--jq` filters, a JSON payload spec, temp-file write/post/cleanup pattern, a fallback command, and a report template. One minor gap: `gh api repos/{owner}/{repo}/pulls/...` provides no `-f owner`/`-f repo` values, so the placeholders would not be substituted as written, placing it just below copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

Steps 1–7 are clearly sequenced with explicit validation and feedback loops: stop-and-ask when no findings exist, stop when no open PR, an inline-to-general-comment fallback on failure, skip-if-note-missing, and a re-read verification that every captured comment_url appears in the updated entry. This matches the anchor with explicit validation steps and error recovery, and the batch nature of posting N comments is covered by these checkpoints.

5 / 5

Progressive Disclosure

There are no bundle files; the single `## Workflow` with numbered steps and per-step blocks is well organized and nothing is buried. However, at roughly 127 lines the detailed daily-note entry-format specification (format, examples, append rules) is long enough that it could arguably live in a one-level-deep reference, and the under-50-line simple-skill exception for a 5 does not apply.

4 / 5

Total

17

/

20

Passed

Description

87%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: it states concrete capabilities in third person and gives an explicit, natural 'Use when' trigger clause tied to both an invocation name and a user phrasing. The only room for improvement is broader synonym coverage (e.g. variations like "comment on the PR") and mentioning the fallback general-comment behavior.

DimensionReasoningScore

Specificity

"Post findings from the most recent review output as inline GitHub PR comments and record them in today's daily note" names two concrete, specific actions covering the skill's full purpose. Minor gaps (fallback general comments, argument filtering) keep it below the comprehensive anchor 5, but it is above anchor 3 since the actions are precise rather than minimal or generic.

4 / 5

Completeness

The description clearly answers both questions: what ("Post findings... as inline GitHub PR comments and record them in today's daily note") and when ("Use when invoked as `$pr-post-review-findings` or when the user asks to post review findings to the current PR") with concrete trigger phrases. The when-clause is explicit and specific, so it is not the anchor-4 case of an improvable 'when'.

5 / 5

Trigger Term Quality

Explicit trigger phrases "$pr-post-review-findings" and "when the user asks to post review findings to the current PR" are natural phrasings users would say. A few natural variations (e.g. "leave PR comments", "inline comments") are missing, so it matches "good keyword coverage; a few natural terms missing" rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The pairing of inline PR comment posting with daily-note recording plus a distinct invocation trigger carves out a clear niche with minimal overlap risk against generic review or PR skills. Triggers are unambiguous, matching the "clear niche with distinct triggers" anchor rather than anchor 4's minor-overlap case.

5 / 5

Total

18

/

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

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

phatblat/dotfiles

Path

.agents/skills/pr-post-review-findings/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.