twenty-partner-triage

Rank the partner-application backlog by net-new value and hand back a short chase-list of applicants worth a personal nudge. Use when the user wants to triage, rank, or prioritize partner applications, find which applicants are worth chasing, run the daily or weekly application review, or asks "who should I reach out to" / "which applications matter". Reads the live partners workspace, read-only, never mutates a record.

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

81%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 well-structured, actionable workflow with strong sequencing and built-in validation, though it leans on an external rank.py script that is not bundled and could use one fully-worked example. Conciseness is good with minor thematic trim possible.

Suggestions

Bundle rank.py (or place it under scripts/) so the load-bearing dependency referenced by the Phase 0 command is actually present and verifiable in the skill bundle.

Add one fully-worked example chase-list entry with realistic placeholder values to make the Phase 2 output template copy-paste concrete.

Trim purely thematic framing lines ('Network upkeep, not the lead path', 'The door stays open for everyone') or fold their decision rule into the existing 'What this is not' section to tighten token use.

Dimension	Reasoning	Score
Conciseness	Mostly lean with no re-explanation of known concepts and all prose carrying guidance, but a few thematic framing lines ('Network upkeep, not the lead path', 'The door stays open for everyone') could be trimmed without losing instruction.	4 / 5
Actionability	Provides an executable command ('python3 "$(dirname "$0")/rank.py"'), a copy-paste output template, and concrete decision rules, but stops short of a fully-worked populated example covering a representative case.	4 / 5
Workflow Clarity	Clear Phase 0→1→2 sequence with explicit validation (credential-stop on missing key, '--selftest'), a feedback loop (re-run self-test after weight/regex edits), and checklists (Phase 1 rules, Phase 2 Rules, Self-check); the batch operation is read-only with validation present so the cap does not apply.	5 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with a one-level credential reference ('../_shared/partner-api.md'), but the load-bearing 'rank.py' dependency is referenced via path yet not present in the bundle, leaving a minor navigation/verification gap.	4 / 5
	Total	17 / 20 Passed

Description

95%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, specific description that clearly states what the skill does and when to use it, with natural trigger phrasing and a tight, distinctive niche. Only marginal room to tighten the 'what' beyond the chase-list framing.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Rank the partner-application backlog by net-new value and hand back a short chase-list'), in third person, with only minor coverage gaps around what 'net-new value' comprises.	4 / 5
Completeness	Explicitly answers both 'what' (rank backlog by net-new value, return a chase-list) and 'when' (a 'Use when...' clause with concrete trigger phrases), satisfying the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrasing including direct user utterances — 'triage, rank, or prioritize partner applications', 'who should I reach out to' / 'which applications matter' — covering synonyms and common variations.	5 / 5
Distinctiveness Conflict Risk	A sharp niche (partner-application triage) with distinct triggers and an explicit scope guard ('Reads the live partners workspace, read-only, never mutates a record'), giving minimal conflict risk.	5 / 5
	Total	19 / 20 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-triage/SKILL.md
Commit: 1749958

Reviewed: 7 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.