CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

manage-pull-requests

Manage Harness Code pull requests via MCP. List, create, update, and merge PRs; add reviewers and submit review decisions (approve / request changes); post, update, and delete comments; read the discussion timeline; and check CI status. Use when asked to open a PR, merge a PR, approve a PR, leave a code review comment, request changes, assign reviewers, or inspect PR checks and activity. Trigger phrases: pull request, PR review, merge PR, approve PR, request changes, add reviewer, PR comments, PR checks, PR activity, code review.

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

Highly actionable content: every MCP call is specified with exact parameters and enums, workflows are sequenced with validation on destructive operations, and troubleshooting anticipates real failure modes. The main improvement opportunities are consolidating the repeated pr_activity guidance and, if the skill grows, splitting the parameter reference or troubleshooting into bundle files.

Suggestions

State the pr_activity read-comments rule once (e.g. in Step 7 and the tools table) and drop the duplicates in Performance Notes and the two Troubleshooting entries, or merge those Troubleshooting entries into one.

Mention the URL shortcut only once (either the MCP Tools Used section or Performance Notes) to save tokens.

If the skill grows, move the per-operation parameter reference or the Troubleshooting catalog into a references/ file and keep SKILL.md as the overview with clearly signaled links.

DimensionReasoningScore

Conciseness

Parameter blocks are concrete with no basic-concept padding, but the pr_activity read-comments rule is repeated four times (tools table, Step 7, Performance Notes, and twice in Troubleshooting) and the URL shortcut is explained twice, so minor trimming is possible. Fits 4 ('minor instances of over-explanation') rather than 5 ('every token earns its place').

4 / 5

Actionability

Every operation has exact tool names, resource types, parameter names, and value enums (e.g. decision: "approved | changereq", method: "merge | squash | rebase | fast-forward"), plus five worked Examples — copy-paste ready guidance covering the common cases, matching the 5 anchor.

5 / 5

Workflow Clarity

Ten clearly sequenced operations with explicit validation before the destructive merge ("Use dry_run: true first to preview the merge", check pr_check "before merging to confirm required checks are green") and Troubleshooting entries that give error-recovery loops for SHA mismatch, rejected review decisions, and missing diff context. This matches the 5 anchor; the destructive-operation cap at 3 does not apply because validation steps are present.

5 / 5

Progressive Disclosure

No bundle files exist and none are referenced; the ~285-line body is well-sectioned (tools table, numbered steps, examples, performance notes, troubleshooting) and easy to navigate. It fits 4 ('good structure; most content appropriately placed') — the full per-operation parameter reference and troubleshooting catalog could eventually move to separate reference files, keeping it below 5's 'appropriately split' ideal.

4 / 5

Total

18

/

20

Passed

Description

88%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: concrete, comprehensive action coverage and an explicit Use-when clause with concrete trigger phrases in third person. The only weaknesses are a few missing natural trigger variations and platform-generic triggers that could collide with other PR skills.

Suggestions

Add trigger phrases for supported operations users would naturally phrase differently, e.g. 'close a PR' and 'CI status' / 'are checks green'.

Qualify generic triggers like 'pull request' or 'code review' with the platform (e.g. 'Harness PR', 'Harness code review') to reduce overlap with generic git/GitHub PR skills.

DimensionReasoningScore

Specificity

"List, create, update, and merge PRs; add reviewers and submit review decisions (approve / request changes); post, update, and delete comments; read the discussion timeline; and check CI status" lists multiple concrete actions with comprehensive coverage of the PR lifecycle, matching the 5 anchor rather than 4's 'minor gaps in coverage'.

5 / 5

Completeness

It explicitly answers what (the full action list) and when ("Use when asked to open a PR, merge a PR, approve a PR, leave a code review comment, request changes, assign reviewers, or inspect PR checks and activity") with concrete trigger phrases, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Trigger phrases ("pull request, PR review, merge PR, approve PR, request changes, add reviewer, PR comments, PR checks, PR activity, code review") plus the Use-when clause give good natural keyword coverage, but a few common user phrasings are missing (e.g. "close a PR", "CI status", "review the diff"). This fits 4 ('a few natural terms missing') better than 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"Manage Harness Code pull requests via MCP" pins a clear niche, but generic triggers like "pull request", "PR review", and "code review" overlap with any other PR-management or git skill, so it is 'mostly distinct; minor overlap risk' (4) rather than minimal conflict risk (5).

4 / 5

Total

18

/

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

harness/harness-ai

Path

plugins/claude/skills/manage-pull-requests/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.