CtrlK
BlogDocsLog inGet started
Tessl Logo

fireflies-core-workflow-b

Search across Fireflies.ai transcripts, use AskFred AI, and build meeting analytics. Use when searching meeting history, querying Fred AI assistant, or aggregating meeting data for reports. Trigger with phrases like "fireflies search", "ask fred", "fireflies analytics", "search meetings", "fireflies AskFred".

64

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/fireflies-pack/skills/fireflies-core-workflow-b/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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, code-driven workflow skill with executable examples and good navigation, weakened primarily by missing validation/confirmation checkpoints around its destructive delete and batch analytics operations.

Suggestions

Add an explicit validation/confirmation checkpoint before the Step 6 thread deletion (e.g., list threads first and confirm the ID) and a results-non-empty check before running Step 5 analytics aggregation.

Flesh out Step 4's cross-meeting example with a concrete filter so it is as executable as the other steps rather than reusing CREATE_THREAD with empty input.

Tighten the illustrative comments (e.g., "Search for quarterly review in the last 30 days") and consolidate the repeated AskFred thread setup across Steps 2–4 to reduce token overhead.

DimensionReasoningScore

Conciseness

The body is mostly lean executable GraphQL/TypeScript with brief per-step intros and assumes Claude's competence; a few illustrative comments and the sparse Step 4 could be trimmed, keeping it just short of fully lean.

4 / 5

Actionability

Provides concrete, mostly copy-paste-ready GraphQL queries and TS snippets for each step, with only minor gaps such as the "your-transcript-id" placeholder and the thin Step 4 cross-meeting example.

4 / 5

Workflow Clarity

Steps are clearly sequenced (1–6) with an error-handling table, but destructive operations (thread deletion in Step 6) and batch analytics run without validation/confirmation checkpoints, capping this dimension at 3 per the rubric.

3 / 5

Progressive Disclosure

Well-organized into Overview, Prerequisites, six numbered steps, Error Handling, Resources, and Next Steps with clearly signaled external doc links and pointers to sibling skills; no bundle files exist, and most content is appropriately inline with only minor organization gaps.

4 / 5

Total

15

/

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, third-person description that clearly states capabilities, use-conditions, and trigger phrases with minimal conflict risk. Its only weakness is that the listed actions are somewhat high-level rather than fully concrete.

DimensionReasoningScore

Specificity

Names the Fireflies domain plus three concrete actions — "Search across Fireflies.ai transcripts, use AskFred AI, and build meeting analytics" — but the actions are moderately high-level rather than fine-grained, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what (search transcripts, use AskFred AI, build analytics) and when ("Use when searching meeting history, querying Fred AI assistant, or aggregating meeting data for reports") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides good natural trigger coverage ("fireflies search", "ask fred", "fireflies analytics", "search meetings", "fireflies AskFred") including a synonym pair, though a few common phrasings like "find meetings" are absent.

4 / 5

Distinctiveness Conflict Risk

Tightly scoped to Fireflies.ai and AskFred with brand-specific triggers, giving it a clear niche and minimal overlap with other skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
Reviewed

Table of Contents

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.