CtrlK
BlogDocsLog inGet started
Tessl Logo

chained-pr

Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

68

Quality

82%

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

87%

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

The content is lean, highly actionable, and uses progressive disclosure well with a verified reference file, but its workflow for the risky rebase/retarget of polluted diffs is missing an explicit validate-retry feedback loop, which caps workflow clarity.

Suggestions

Add an explicit feedback loop for polluted-diff cleanup in Execution Steps or Decision Gates (e.g., "After retarget/rebase, run `gh pr view` to confirm only the current unit's lines remain; if extra diff persists, rebase again"), which would lift workflow_clarity to 3.

Optionally surface a short inline validation checkpoint after step 5 so the verify->fix->retry cycle is explicit rather than implied.

DimensionReasoningScore

Conciseness

Lean body with no padding or explanation of concepts Claude already knows; every section (Hard Rules, Decision Gates, Execution Steps) earns its tokens with actionable content and defers detail to the reference file.

3 / 3

Actionability

Concrete, executable guidance throughout: specific line thresholds ("400 changed lines", "≤60 minutes"), concrete markers (`size:exception`, `📍`), and copy-ready `gh pr` commands in the reference, with clear decision-gate actions.

3 / 3

Workflow Clarity

Execution steps are clearly sequenced and step 5 includes verification (CI/tests/docs/manual checks, rollback scope, clean diff), but destructive/batch git operations like retargeting polluted diffs ("retarget or rebase until only the current work unit appears") lack an explicit validate->fix->retry feedback loop, capping workflow clarity at 2 per the destructive-operations rule.

2 / 3

Progressive Disclosure

Well-organized SKILL.md overview with a single clearly-signaled one-level-deep reference (references/chaining-details.md, which exists and contains the deferred diagrams/commands/template), matching the clear-overview-with-one-level-references anchor.

3 / 3

Total

11

/

12

Passed

Description

77%

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 specific, distinct, and rich in natural trigger terms, but frames the trigger via a leading "Trigger:" label rather than an explicit "Use when..." clause, leaving completeness just short of the top anchor.

Suggestions

Replace the leading "Trigger:" label with an explicit "Use when..." clause (e.g., "Use when a PR may exceed 400 changed lines, when SDD forecasts a size-budget risk, or when the user asks for stacked/chained PRs or review slices.") to satisfy the explicit-when anchor for completeness.

Keep the concrete action verbs but ensure the trigger conditions read as guidance Claude should follow rather than a bare label.

DimensionReasoningScore

Specificity

Names concrete actions ("split oversized changes", "chained PRs", "protect review focus") rather than vague verbs, matching the multi-action anchor.

3 / 3

Completeness

Explicitly states the trigger ("Trigger: PRs over 400 lines, stacked PRs, review slices") and the what, but the trigger is asserted rather than framed as "Use when..." guidance; the when is present but borderline-implied, capping at 2.

2 / 3

Trigger Term Quality

Surfaces natural user phrasings ("PRs over 400 lines", "stacked PRs", "review slices", "chained PRs") that users would actually say, with good variation coverage.

3 / 3

Distinctiveness Conflict Risk

Clear niche around oversized/stacked PR review-load control with distinct triggers (400-line threshold, stacked/chained) unlikely to conflict with generic PR skills.

3 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Gentleman-Programming/gentle-ai
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.