CtrlK
BlogDocsLog inGet started
Tessl Logo

prepare-paperclip-pr

Prepare a Paperclip branch for PR with commits, template body, and checks.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/prepare-paperclip-pr/SKILL.md
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.

The content is a well-sequenced, highly actionable procedure with explicit validation checkpoints and genuine review feedback loops, and it stays lean by assuming competence. Its main weaknesses are minor redundancy (the duplicated ALL-CAPS Greptile instruction and the 'Hard rules' section) and a couple of places where concrete commands are left implicit.

Suggestions

Delete the ALL-CAPS 'RUN GREPTILE UNTIL IT GETS TO 5/5 - DO NOT STOP UNTIL...' paragraph — it duplicates the first bullet of section 5 — and instead emphasize the termination criteria once, e.g. 'Stop only when Greptile is 5/5, all tests and verification checks pass, and there are no merge conflicts.'

Consolidate the 'Hard rules' section into the steps where each rule already appears (sections 1 and 4) rather than repeating them, keeping a single source of truth.

Make the remaining vague steps concrete: give the exact rebase command form (e.g. 'git fetch <remote> && git rebase <remote>/master') and a minimal 'gh pr create' invocation with the --title/--body template shape.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — imperative bullets, exact commit trailer, numeric thresholds — with no re-teaching of known concepts. It falls short of lean/5 because of redundancy: the ALL-CAPS 'RUN GREPTILE UNTIL IT GETS TO 5/5 - DO NOT STOP...' restates the preceding bullet, and the 'Hard rules' section duplicates rules already given in sections 1 ('no orphaned stashes... no dropped files') and 4 ('Record the PR URL immediately').

4 / 5

Actionability

Concrete, mostly executable guidance throughout: 'git rev-parse --git-dir', 'git branch --show-current', 'gh', the exact trailer 'Co-Authored-By: Paperclip <noreply@paperclip.ing>', the 'under 100 changed files' limit, 'max 20 turns', and the CONTRIBUTING.md URL. Minor gaps keep it below 5: no copy-paste 'gh pr create' form, and 'rebase (or otherwise replay) your branch' leaves the mechanism open rather than giving an exact command.

4 / 5

Workflow Clarity

A clearly numbered 0–6 sequence with explicit validation checkpoints (worktree verification, post-rebase re-verification 'build/tests... still pass', the guardrails checklist) and true feedback loops with defined termination criteria — 'repeat until Greptile gives 5/5 with zero unresolved comments (max 20 turns). Do not stop early' — plus renumber/re-run recovery for migration conflicts. This matches the anchor 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists for complex processes'.

5 / 5

Progressive Disclosure

The body is a well-sectioned procedure with one-level-deep pointers only (CONTRIBUTING.md URL, /greploop and /prcheckloop skills) and no bundle files to organize, which is appropriate for a ~80-line procedural skill. It misses 5 due to minor organization gaps — the redundant 'Hard rules' section re-states earlier rules instead of consolidating them, slightly muddying navigation.

4 / 5

Total

17

/

20

Passed

Description

58%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 compact and domain-anchored with several concrete components, but it lacks any explicit 'when to use' trigger guidance and omits common trigger synonyms such as 'pull request'. It is distinguishable from generic skills primarily through the 'Paperclip' term.

Suggestions

Add a 'Use when...' clause naming the triggering situations (e.g., 'Use when finishing work on a Paperclip branch and turning it into a reviewed, green pull request').

Include natural trigger synonyms users would actually say — 'pull request' (spelled out), 'open a PR', 'rebase', 'PR review' — to broaden keyword coverage.

Replace the vague 'checks' with the concrete things it actually runs (Greptile review loop, CI verification), which improves both specificity and trigger quality.

DimensionReasoningScore

Specificity

Quotes 'commits, template body, and checks' alongside 'Prepare a Paperclip branch for PR' — several concrete components are named, but 'checks' is generic and the wider procedure (rebase, review loops, reporting) is uncovered. It sits above the '1-2 concrete actions' anchor (3) because it lists several specific items, but below anchor 5 due to coverage gaps.

4 / 5

Completeness

The 'what' is clear (prepare a branch for PR via commits, template body, checks) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3 ('clear what but when is missing or only weakly implied').

3 / 5

Trigger Term Quality

Relevant keywords are present ('PR', 'commits', 'branch', 'Paperclip'), matching 'Works with PDF files' in spirit, but common natural variations are missing — 'pull request' never appears spelled out, nor do 'open a PR', 'rebase', or 'review'. Matches the 'some relevant keywords but missing common variations or synonyms' anchor exactly.

3 / 5

Distinctiveness Conflict Risk

'Paperclip branch' and 'paperclipai/paperclip' context carves a clear niche, but the generic terms 'PR' and 'commits' leave minor overlap risk with general git/PR-preparation skills — 'mostly distinct; minor overlap risk with closely related skills'. Not anchor 5 because triggers like 'PR' and 'checks' are not uniquely distinctive on their own.

4 / 5

Total

14

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
paperclipai/paperclip
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.