twenty-partner-application-triage

Rank the partner-application backlog by net-new value and surface a short chase-list of high-value applicants who haven't booked a call. Use when the user wants to triage, rank, or prioritize partner applications, find which applicants are worth chasing, run the daily/weekly application review, or asks "who should I reach out to" / "which applications matter". Reads the live partners workspace; read-only.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear phased workflow, executable commands, and concrete output templates. Its weaker spots are verbosity from philosophical framing and a monolithic structure with no progressive disclosure to supporting files.

Suggestions

Trim editorializing prose (e.g. "The door stays open for everyone", the "Build skill → trust it → port" paragraph) to motivation-only one-liners so every line instructs.

Move the inline scoring formula and ranked-entry JSON field schema into rank.py's own docstring or a short reference file, keeping SKILL.md as an overview that links one level deep.

If rank.py is a real bundle file, place it under scripts/ and reference it by path so the progressive-disclosure structure is verifiable; if it is not bundled, state that explicitly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and action-oriented, but padded with editorializing prose ("The door stays open for everyone", "Build skill → trust it → port the cheap part. Don't build both.") that frames philosophy rather than instructing; could be tightened without losing clarity, so it sits below the lean/3 anchor.	2 / 3
Actionability	Provides a copy-paste command (python3 "$(dirname "$0")/rank.py"), an exact ranked-entry JSON field schema, the precise scoring formula, and a copy-paste output template — concrete and executable rather than vague.	3 / 3
Workflow Clarity	Clear Phase 0 → 1 → 2 sequence with an explicit validation checkpoint (stop on missing-credentials error and name the key) and a --selftest feedback loop; the operation is read-only so the destructive-cap does not apply.	3 / 3
Progressive Disclosure	Well-sectioned but monolithic: the scoring formula, JSON field schema, and output template all live inline with no reference files in the bundle to defer to (rank.py is referenced but not present under references/scripts/assets), so it is below the one-level-deep/3 anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that states concrete actions, gives explicit "Use when" triggers with natural keyword variants, and carves out a distinctive niche. It cleanly satisfies all four dimensions with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Rank the partner-application backlog by net-new value" and "surface a short chase-list of high-value applicants" — matching the multiple-specific-actions anchor; not below because it is not merely a domain label.	3 / 3
Completeness	Explicitly answers both what (rank backlog by net-new value, surface chase-list) and when via an explicit "Use when the user wants to triage, rank, or prioritize..." clause; not 2 because the trigger guidance is explicit, not implied.	3 / 3
Trigger Term Quality	Covers natural phrasings a user would actually say — "triage, rank, or prioritize partner applications", "find which applicants are worth chasing", "run the daily/weekly application review", "who should I reach out to" / "which applications matter" — broad coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (partner-application triage, un-booked high-value applicants, Twenty partners workspace) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: twentyhq/twenty
Path: packages/twenty-apps/internal/twenty-partners/src/skills/twenty-partner-application-triage/SKILL.md
Commit: bb4e427

Reviewed: 6 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.