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

83%

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

80%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.

A tight, highly actionable skill body with good structure and a verified bundled script. Its main weakness is the missing validation checkpoint for what is a destructive edit to pyproject.toml, which caps workflow clarity.

Suggestions

Add an explicit validation step to the Workflow, e.g. run with --dry-run first and review the diff before applying, then verify pyproject.toml still parses after the edit.

Fold the redundant one-line intro into the title to avoid restating the description, tightening conciseness toward anchor 5.

Note git/version-control as a recovery safeguard before modifying pyproject.toml, giving the destructive operation a clear rollback checkpoint.

Dimension	Reasoning	Score
Conciseness	Lean and mostly efficient with no padding or explanations of concepts Claude already knows; the one-line intro and 'When to Use' section lightly restate the description, which is a minor trim opportunity rather than anchor-5 perfection.	4 / 5
Actionability	Provides copy-paste-ready executable commands for both venv and activated-venv invocation, a complete options table with flags, and a concrete manual fallback; the referenced bundled script exists at scripts/update_entry_points.py.	5 / 5
Workflow Clarity	The sequence is clear (run the script, with the four sub-steps it performs), but this destructively replaces sections of pyproject.toml and the workflow lacks an explicit validation/verification checkpoint (e.g., run --dry-run first, confirm the diff), so the destructive-operation cap of 3 applies.	3 / 5
Progressive Disclosure	A short, single-purpose skill under 50 lines with well-organized sections (When to Use, Workflow, Options, Manual Fallback) and a single, clearly signaled one-level reference to the bundled script that exists in scripts/.	5 / 5
	Total	17 / 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 precise, well-scoped description that clearly states what it does and when to use it, with natural trigger phrases for the target audience. Minor room for broader keyword synonyms, but overall strong.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Generate ... entry points', 'update pyproject.toml') tied to a specific mechanism (decorators → entry point groups → config file); falls between anchor 3 (1-2 actions) and 4 (several) but the mechanism-level detail pushes it noticeably above the midpoint.	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 concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Includes natural developer phrases like 'adding new sources or segments' and 'entry points are out of sync with the codebase' alongside technical terms; good coverage, though it lacks synonyms or file-extension variants that would reach 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche scoped to TalkPipe's specific decorators and pyproject.toml entry-point sections, with distinct triggers and minimal overlap risk with unrelated skills.	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: 14049ad

Reviewed: 2 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.