kol-discovery

Find Key Opinion Leaders (KOLs) in a given domain by combining web research with LinkedIn post search. Given a company/idea and target domain, generates authority keywords, searches LinkedIn posts to find prolific authors with high engagement, and merges with web-researched influencers. Use when someone wants to "find influencers in X space" or "who are the KOLs for Y industry."

Quality

89%

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

88%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-built operational skill: executable commands, complete input/output schemas, and a phased workflow with real validation gates and refinement loops for a costly batch pipeline. The main polish opportunities are trimming duplicated content and slightly tighter signposting of the bundle script.

Suggestions

Remove the 'Trigger phrases' subsection (it duplicates the frontmatter description) and fold the single alternate invocation example into Phase 2 to trim tokens.

Replace the second full command example with a one-line note about pointing --config at an existing client config, keeping Phase 2 as the canonical invocation.

Add a brief line in 'Tools Required' or Phase 2 explicitly identifying scripts/kol_discovery.py as the bundled pipeline script so the bundle file is clearly signposted.

Dimension	Reasoning	Score
Conciseness	The body is efficient — phase-structured, domain-specific guidance (authority keywords vs pain-language, config schema, scoring formula) that Claude would not already know, with no padded conceptual explanation. It misses anchor 5 because of a few trimmable pieces: the 'Example Usage' trigger-phrase list duplicates the frontmatter description, and the second invocation example largely repeats the Phase 2 command.	4 / 5
Actionability	Guidance is fully executable: a copy-paste-ready command with every flag documented, a complete config JSON structure, a concrete web-KOL JSON example, an explicit Apify actor name, and a full CSV output-column spec. This matches the anchor for executable commands covering the common cases; anchor 4's 'minor gaps' do not apply.	5 / 5
Workflow Clarity	Phases 0–4 are clearly sequenced with explicit validation checkpoints for a paid batch operation: user approval of keywords before running, "Always run with --test first", cost confirmation, and a Phase 3 review/refine feedback loop (refine keywords, add exclusions, lower thresholds). This matches the anchor-5 pattern of explicit validation plus error-recovery loops, and avoids the batch-operation cap at 3.	5 / 5
Progressive Disclosure	Structure is good: the SKILL.md is an overview, the heavy implementation is correctly delegated to the single bundle script (scripts/kol_discovery.py, which exists), and there are no nested references — so above anchor 3. It stops short of anchor 5 due to minor organization gaps: the trigger-phrase and duplicate-command sections add inline length without structural value, and the script is referenced only via a command path rather than clearly signposted as the skill's bundle file.	4 / 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: third-person voice, multiple concrete actions, and an explicit 'Use when' clause with natural trigger phrases. The only improvements are adding output-side specifics (ranked KOL list) and a few more synonyms such as 'thought leaders'.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "generates authority keywords, searches LinkedIn posts to find prolific authors with high engagement, and merges with web-researched influencers" — going beyond the 1-2 actions of anchor 3. It falls short of anchor 5 because it omits part of the capability surface, e.g. scoring/ranking the KOLs and producing an output list.	4 / 5
Completeness	It clearly answers "what" (keyword generation, LinkedIn post search, author finding, merging) and "when" with an explicit "Use when someone wants to..." clause containing concrete quoted trigger phrases — a direct match for the anchor-5 example. It is not anchor 4 since the 'when' is already fully explicit with specific trigger wording.	5 / 5
Trigger Term Quality	It includes natural phrases users would actually say — "find influencers in X space", "who are the KOLs for Y industry" — plus both "KOLs" and "influencers" as synonyms. Not anchor 5 because common variations like "thought leaders", "industry experts", or "discover experts in" are missing.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche — KOL/influencer discovery via LinkedIn post search combined with web research — with distinct trigger phrasing, so the risk of firing for an unrelated skill is minimal. Adjacent anchor 4's "minor overlap risk with closely related skills" is not a better fit because the LinkedIn + KOL framing is highly specific.	5 / 5
	Total	18 / 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: gooseworks-ai/goose-skills
Path: skills/social/capabilities/kol-discovery/SKILL.md
Commit: cc3e518

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.