CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-to-green

Bring a pull request to green by syncing with main, resolving conflicts safely, and fixing failing checks with CausalPy conventions.

63

Quality

73%

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 ./.agents/skills/pr-to-green/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 lean, well-structured procedural workflow with concrete commands, explicit validation checkpoints, feedback loops, and escalation checklists — strong across the board, with only minor conciseness and progressive-disclosure refinements possible.

DimensionReasoningScore

Conciseness

The body is procedural and avoids explaining concepts Claude already knows, with only minor padding such as "Each subagent runs in its own context window and returns a condensed result"; not a 5 because a few sentences could be trimmed.

4 / 5

Actionability

Concrete executable commands appear throughout ("gh pr view <number>", "git rebase upstream/<base-branch>", "prek run --all-files", "git diff --name-only --diff-filter=U") alongside some high-level direction like "resolve conflicts file-by-file with intent preservation"; not a 5 because some guidance remains abstract.

4 / 5

Workflow Clarity

The six-step workflow is clearly sequenced with explicit validation checkpoints, a feedback loop ("loop back to step 3"), and escalation checklists for destructive/batch operations like rebase and push, matching the top anchor.

5 / 5

Progressive Disclosure

The body is well-sectioned with no nested references and no bundle files present, but the ~135-line subagent and escalation detail could be split one level deep into reference files; not a 5 because the longer doc is not partitioned into one-level references.

4 / 5

Total

17

/

20

Passed

Description

66%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 specific and uses natural developer trigger terms within a well-scoped CausalPy niche, but it omits an explicit "Use when…" trigger clause, which limits its completeness and weakens when-to-use guidance.

Suggestions

Append an explicit "Use when…" clause naming concrete trigger phrases (e.g., 'Use when a PR is failing CI, behind main, or has merge conflicts') to lift completeness above 3.

Add common synonyms such as 'rebase', 'merge conflicts', and 'CI' to broaden trigger-term coverage.

Add a distinguishing qualifier versus generic git/dev skills (e.g., 'with CausalPy test, docs, and packaging conventions') to reduce overlap risk within the CausalPy skill family.

DimensionReasoningScore

Specificity

Lists three concrete actions — "syncing with main", "resolving conflicts safely", and "fixing failing checks" — which matches several-specific-actions with minor gaps; not a 5 because the actions are somewhat broad rather than comprehensive.

4 / 5

Completeness

The "what" is clear ("Bring a pull request to green by…") but there is no explicit "Use when…" clause, so the "when" is only weakly implied — per the rubric a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural developer phrasing like "pull request", "green", "syncing with main", "conflicts", and "failing checks" gives good coverage; not a 5 because common synonyms like "rebase" and "merge conflicts"/"CI" are missing.

4 / 5

Distinctiveness Conflict Risk

The CausalPy-specific PR-greening niche is mostly distinct, but it could overlap with other CausalPy dev/git skills, so minor overlap risk remains rather than a clear isolated niche.

4 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pymc-labs/CausalPy
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.