meta-issue-to-pr-autopilot

[DEPRECATED] Issue-to-PR autopilot — opens a PR via `gh`, runs a sub-agent fix loop, and writes to git. Disabled pending the E5 bounded sub-agent contract + side-effect ledger (plan §3.1 A8 / §5.3 E4): no risk metadata enforcement, no per-step budget, no rollback path. Do not re-enable without `metadata.opensquilla.risk: high` + capabilities {vcs, filesystem-write, network-write, subprocess} and a saga-style compensation step.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./src/opensquilla/skills/exp/meta-issue-to-pr-autopilot/SKILL.md

Quality

Content

72%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 body is commendably concise and well-structured for a simple meta-skill, with a useful concrete fallback. Its weakness is actionability and workflow clarity: the main happy path is described abstractly and lacks the validation/checkpoint feedback loops that PR-opening and git-writing operations warrant.

Suggestions

Make the main flow actionable by showing the concrete `gh` invocations and the sub-agent/summarize step signatures rather than only narrating them.

Add explicit validation checkpoints (e.g., verify the patch builds/tests pass and the PR body is non-empty) before opening the PR, with a fix-and-retry loop on failure.

Note the conditions under which to fall back to the manual `gh` path so the fallback section functions as a true error-recovery branch.

Dimension	Reasoning	Score
Conciseness	The body is a lean overview plus a compact fallback with no explanation of concepts Claude already knows; every line earns its place, matching the 'lean and efficient' anchor.	5 / 5
Actionability	The fallback gives concrete commands ('gh issue view', 'gh pr create') but the main flow only describes steps at a high level ('delegates the fix to sub-agent', 'drafts a PR description') without executable specifics, landing between minimal and mostly-executable guidance.	3 / 5
Workflow Clarity	A rough four-step sequence is sketched (triage → sub-agent → summarize → open PR) plus a fallback path, but for destructive/batch git and PR operations there are no validation checkpoints or error-recovery feedback loops, so per the rubric cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references and uses well-organized sections (overview + Fallback), so the simple-skill exception lets progressive disclosure score 5.	5 / 5
	Total	16 / 20 Passed

Description

42%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 distinctive about its mechanism but is framed almost entirely as a deprecation notice, crowding out any natural user-trigger language and an explicit usable 'when' clause. It reads as an internal safety warning rather than a discoverable skill description.

Suggestions

Add an explicit 'Use when…' clause with natural trigger phrases (e.g., 'Use when the user asks to turn a small, well-scoped GitHub issue into a pull request') so the 'when' is present while the deprecation caveat remains.

Replace internal jargon ('bounded sub-agent contract', 'side-effect ledger', 'saga-style compensation step') with plain-language capability terms so users can naturally match the skill to their request.

Lead with the functional description and relegate the deprecation/gating rationale to a trailing sentence, keeping the concrete actions ('opens a PR via gh', 'sub-agent fix loop') prominent.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'opens a PR via `gh`', 'runs a sub-agent fix loop', 'writes to git' — giving several specific operations with only minor coverage gaps, which fits the 'lists several specific actions' anchor above a score of 3.	4 / 5
Completeness	It states a clear 'what' (issue-to-PR autopilot) but the 'when' is expressed as a prohibition ('Do not re-enable without…') rather than any explicit user-facing trigger guidance, so it lacks a usable 'when' clause and falls below the 'clear what, weak/missing when' anchor at 3.	2 / 5
Trigger Term Quality	The text is dominated by deprecation and internal-contract jargon ('bounded sub-agent contract', 'side-effect ledger', 'saga-style compensation step') with only generic keywords ('issue', 'PR'), missing the natural phrases a user would say; this sits between the generic-keyword and some-relevant-keyword anchors, noticeably below midpoint.	2 / 5
Distinctiveness Conflict Risk	The issue-to-PR autopilot niche with gh/sub-agent/summarize composition is mostly distinct from other skills with only minor overlap risk against general github skills, matching the 'mostly distinct' anchor above 3.	4 / 5
	Total	12 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/exp/meta-issue-to-pr-autopilot/SKILL.md
Commit: 94ac35e

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.