collector-hand-skill

Expert knowledge for AI intelligence collection — OSINT methodology, entity extraction, knowledge graphs, change detection, and sentiment analysis

Quality

67%

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 ./crates/openfang-hands/bundled/collector/SKILL.md

Quality

Content

77%

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

The body is a well-structured, highly actionable methodology reference with concrete schemas, query templates, scoring rules, and a sequenced workflow plus validation checklist. Its main weaknesses are verbosity in the template sections and a fully monolithic layout with no progressive disclosure via separate files.

Suggestions

Move the extensive query-template blocks and the full report markdown template into a references/ file (e.g., QUERY_TEMPLATES.md, REPORT_TEMPLATE.md) and link to them from SKILL.md to improve progressive disclosure and token efficiency.

Trim redundant query-string examples within each focus area to the 2-3 highest-value patterns to tighten the body.

Dimension	Reasoning	Score
Conciseness	The body is dense reference material that largely avoids explaining concepts Claude already knows, but it is voluminous — five query-template blocks of 5-6 strings each and a full ~35-line report markdown template — so it 'could be tightened' rather than earning the 'every token earns its place' bar of a 3.	2 / 3
Actionability	It provides concrete, copy-paste-ready guidance: exact search-query strings, JSON entity and relation schemas, discrete sentiment scoring values (+2 to -2), and significance tiers — matching 'Fully executable... specific examples; copy-paste ready', with the absence of code acceptable for this instruction-only skill.	3 / 3
Workflow Clarity	The 6-step collection cycle is clearly sequenced and includes an explicit feedback step, and the source-evaluation checklist acts as a validation gate with a concrete threshold rule ('If a claim fails 3+ checks, downgrade'), matching 'Clear sequence with explicit validation steps; feedback loops... checklists for complex processes'.	3 / 3
Progressive Disclosure	The content is well-sectioned with headers but is a monolithic ~260-line SKILL.md with no bundle files and no external references; the under-50-line simple-skill carve-out does not apply, so this fits 'content that should be separate is inline' rather than the reference-split structure of a 3.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 clearly identifies a distinctive niche and lists relevant capability areas, but it reads as a topic list rather than concrete actions and omits any 'Use when...' trigger guidance. It is solid but lacks the explicit when-to-use clause needed for full marks.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when researching a company/person, monitoring competitors, or building an OSINT knowledge graph').

Reframe the capability list with concrete verbs (e.g., 'Extract entities, build knowledge graphs, detect changes, score sentiment') instead of the 'Expert knowledge for' topic framing.

Dimension	Reasoning	Score
Specificity	The description names a domain ('AI intelligence collection') and several sub-areas ('OSINT methodology, entity extraction, knowledge graphs, change detection, and sentiment analysis'), but frames them as topics via 'Expert knowledge for' with no concrete verbs, matching 'Names domain and some actions, but not comprehensive' rather than the multi-action list of a 3.	2 / 3
Completeness	It clearly states what the skill covers, but there is no 'Use when...' clause or equivalent explicit trigger guidance for when to use it, so per the judging guidelines completeness is capped at 2 ('Has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	It mixes natural terms a user might say ('sentiment analysis', 'change detection') with technical jargon ('OSINT methodology', 'knowledge graphs') and lacks common phrasings, fitting 'Some relevant keywords but missing common variations' rather than the full coverage of a 3 or the pure-jargon of a 1.	2 / 3
Distinctiveness Conflict Risk	'AI intelligence collection — OSINT methodology' is a clear, narrow niche with distinctive vocabulary unlikely to overlap with or trigger other skills, matching 'Clear niche with distinct triggers; unlikely to conflict' and well above the generic 1/2 anchors.	3 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: RightNow-AI/openfang
Path: crates/openfang-hands/bundled/collector/SKILL.md
Commit: acf2587

Reviewed: about 8 hours 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.