discovery

Analyzes discovery call transcripts from Attio (primary) and Granola (secondary) against the Discovery Questions Tracker template, creates or appends to a Google Sheet in the Discovery folder with full scoring, customer answers, and evidence, and posts a summary note to the Attio company record. Outputs an xlsx with tabs matching the original spreadsheet template. Use when the user wants to process a discovery call, fill out discovery questions, create a discovery doc, or run /discovery.

Quality

75%

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 ./discovery/SKILL.md

Quality

Content

57%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 thorough, largely actionable multi-phase workflow with concrete MCP calls and scripts, weakened by a missing validation loop around batch sheet operations, a broken reference to a non-existent XLSX_STRUCTURE.md (whose content is inlined), and notable duplication of the Technical Environment field list across three sections.

Suggestions

Add validation checkpoints to the batch sheet operations: after Path A upload, verify the converted Google Sheet opened with all 11 tabs and a working link; before Path B re-upload, back up the existing sheet and verify the cell modifications are correct.

Resolve the dangling XLSX_STRUCTURE.md reference — either create that bundle file holding the 11-tab specification and trim the inlined spec from SKILL.md, or remove the reference and keep the specification inline.

Define the 14-field Technical Environment list and the 8 maturity dimensions once, then reference them from the note template and the Phase 6 report to remove roughly 40 lines of verbatim repetition.

Dimension	Reasoning	Score
Conciseness	Mostly actionable rather than explanatory (it does not define Attio/Granola/openpyxl), but the 14-field Technical Environment list is repeated verbatim three times (Phase 3 table, note template, Phase 6 report) and the 8 maturity dimensions twice — structural redundancy that goes beyond minor tightening.	3 / 5
Actionability	Provides exact MCP tool calls with parameters, a copy-paste Ruby upload script with real paths and folder ID, and concrete drive_manager.rb commands, but leaves the central deliverable — the 11-tab openpyxl workbook — as a structural spec rather than executable code, a notable gap.	4 / 5
Workflow Clarity	The 6-phase sequence with numbered steps and a top-level flow diagram is clear, but the batch/destructive operations (Path A upload with no conversion verification; Path B modifying and re-uploading an existing shared spreadsheet with no backup or pre-upload validation) lack validation checkpoints, capping this dimension at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	Internal phase structure is well-organized, but the referenced 'XLSX_STRUCTURE.md alongside this skill' is a dangling reference (no such file or bundle directory exists) and the 11-tab specification it claims to defer is actually inlined, matching the level-3 anchor of content that should be separate being inline with a non-functional reference.	3 / 5
	Total	13 / 20 Passed

Description

92%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 concretely states both what the skill does and when to use it, with a niche clearly tied to specific tools and a slash command. Its only weakness is trigger-term breadth: it lists several good phrases but omits common synonyms and file-extension variants that would make discovery more robust.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyzes discovery call transcripts', 'creates or appends to a Google Sheet ... with full scoring, customer answers, and evidence', 'posts a summary note to the Attio company record', 'Outputs an xlsx with tabs' — giving comprehensive coverage of the workflow, matching the level-5 anchor.	5 / 5
Completeness	Explicitly answers 'what' with several concrete actions and 'when' via a full 'Use when the user wants to process a discovery call, fill out discovery questions, create a discovery doc, or run /discovery' clause, matching the level-5 anchor exactly.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('process a discovery call', 'fill out discovery questions', 'create a discovery doc', 'run /discovery') plus product names Attio/Granola, but lacks synonyms/variations (e.g. 'discovery meeting', 'qualification call') and file-extension triggers, so it sits above the midpoint but short of fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (discovery-call transcript processing tied to named tools Attio/Granola, a named Discovery Questions Tracker template, and a /discovery command) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 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
skill_md_line_count	SKILL.md is long (545 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: llaskin/skill-eval-test
Path: discovery/SKILL.md
Commit: 11e5abd

Reviewed: ~24 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.