update-entry-points

Generate talkpipe.sources and talkpipe.segments entry points from @register_source/@register_segment decorators and update pyproject.toml. Use when adding new sources or segments to TalkPipe, or when entry points are out of sync with the codebase.

1.01x

Quality

87%

Does it follow best practices?

Impact

100%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

87%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 exemplary in efficiency and actionability — exact commands, accurate options, and a concrete fallback. The one real weakness is workflow safety: a pyproject.toml-rewriting operation presented without any validation/verification step, relying on the reader to discover --dry-run on their own.

Suggestions

Sequence the workflow as a feedback loop: run with --dry-run first, review the printed diff, then run for real — making the existing dry-run flag an explicit validation checkpoint rather than just an option-table row.

Add a post-update verification step, e.g. confirm the generated entry points parse (a TOML validity check or "git diff pyproject.toml" review) before declaring the task complete.

In the Manual Fallback, warn that the replacement spans from [project.entry-points."talkpipe.sources"] to the end of the entry-point block (not literally end of file) if other sections follow, or advise backing up pyproject.toml before the manual edit.

Dimension	Reasoning	Score
Conciseness	The ~44-line body is lean and assumes competence: no concept explanations, no padding, and each section (When to Use, Workflow, Options, Manual Fallback) earns its place. The two invocation variants are practical alternatives rather than verbosity.	5 / 5
Actionability	Copy-paste ready commands (".venv/bin/python .cursor/skills/update-entry-points/scripts/update_entry_points.py"), an options table whose flags match the bundled script's actual argparse interface, and a concrete manual fallback with exact commands cover the common cases fully.	5 / 5
Workflow Clarity	The sequence is present (run script, options, manual fallback if it fails), but this is a destructive/batch operation that rewrites pyproject.toml with no validation checkpoint: --dry-run is documented only as an option, never sequenced as a verify step, and there is no post-update verification. Per the rubric, destructive/batch workflows without validation are capped at 3.	3 / 5
Progressive Disclosure	A simple sub-50-line, single-task skill with well-organized sections and no need for external references; the one referenced bundle script (scripts/update_entry_points.py) exists and its documented interface matches the body. Satisfies the simple-skill exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

87%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 actions, explicit trigger guidance, and a clearly bounded niche. The only minor gap is that trigger coverage could include a few more natural synonyms a user might use when registering new sources or segments.

Dimension	Reasoning	Score
Specificity	"Generate talkpipe.sources and talkpipe.segments entry points from @register_source/@register_segment decorators and update pyproject.toml" lists several concrete, named actions with a specific file target. It falls short of a 5 because coverage is narrower than the comprehensive exemplar (no mention of scanning or preserving other content, and only two top-level actions).	4 / 5
Completeness	Explicitly answers both what ("Generate ... entry points ... and update pyproject.toml") and when ("Use when adding new sources or segments to TalkPipe, or when entry points are out of sync with the codebase") with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	"adding new sources or segments", "entry points", "out of sync" are phrases a user would naturally say in this situation. Not a 5 because common variations/synonyms (e.g., "register a source", "plugin registration") are absent; not a 3 because coverage is good rather than partial.	4 / 5
Distinctiveness Conflict Risk	"talkpipe.sources", "@register_source/@register_segment decorators", and "TalkPipe" define a clear niche with distinct triggers and virtually no risk of firing for the wrong skill.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: sandialabs/talkpipe
Path: .cursor/skills/update-entry-points/SKILL.md
Commit: 4b4d232

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.