discovery-process

Run a full discovery cycle from problem hypothesis to validated solution. Use when a team needs a structured path through framing, interviews, synthesis, and experiments.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/discovery-process/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 strongly actionable, well-sequenced workflow with explicit validation checkpoints, but it is held back by redundancy (a duplicated summary tree and a repeated references list) and by references to bundle files that are not actually present.

Suggestions

Remove the end-to-end summary tree and the consolidated references list, or move them to a separate overview file, since both duplicate the per-phase detail already in the body.

Either ship the referenced template.md and examples/sample.md in the bundle or drop the references to them so navigation is not broken.

Trim the 'Why This Works' and 'Anti-Patterns (What This Is NOT)' sections to a few bullets to reduce token cost without losing the 'When NOT to use' guidance.

Dimension	Reasoning	Score
Conciseness	Most content is operational detail rather than concepts Claude already knows, but the end-to-end summary tree and the references section both restate the inline phase detail, and 'Why This Works'/'Anti-Patterns' add padding that could be trimmed.	2 / 3
Actionability	It provides concrete, copy-paste-ready guidance: an interview-question template ('Tell me about the last time you...'), a structured note-taking template, the problem-hypothesis fill-in format, named experiment types, and explicit decision criteria.	3 / 3
Workflow Clarity	Six phases are clearly sequenced, each with a goal, activities, and outputs, plus three explicit decision points with if/else branches and time impacts forming real validation feedback loops.	3 / 3
Progressive Disclosure	Sections are well organized and peer-skill references stay one level deep, but the file is a ~500-line monolith and the bundle files it points to (template.md, examples/sample.md) do not exist in the bundle.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 cleanly answers both what and when with an explicit 'Use when' trigger, but its named activities are abstract categories and it lacks the natural-term breadth and distinctiveness needed for top marks.

Suggestions

Swap abstract phase labels for concrete actions, e.g. 'Frame a problem hypothesis, run 5-10 customer interviews, synthesize pain points, and design validation experiments.'

Add common natural trigger phrasings users would say verbatim, such as 'user research', 'customer discovery', or 'validate a hypothesis before building'.

Sharpen distinctiveness by signaling the orchestration scope, e.g. 'Use when you need the full end-to-end cycle, not a single interview or synthesis step.'

Dimension	Reasoning	Score
Specificity	It names the discovery domain and several activities ("framing, interviews, synthesis, and experiments") but these are high-level phase categories rather than the granular concrete actions the top anchor calls for.	2 / 3
Completeness	It explicitly states both what it does ("Run a full discovery cycle from problem hypothesis to validated solution") and when to use it ("Use when a team needs a structured path through framing, interviews, synthesis, and experiments").	3 / 3
Trigger Term Quality	Terms like "discovery cycle", "problem hypothesis", and "interviews" are natural PM vocabulary, but common variations such as "user research", "customer discovery", or "validate a hypothesis" are missing.	2 / 3
Distinctiveness Conflict Risk	The end-to-end orchestration framing is fairly niche, but it overlaps with the individual component skills it orchestrates (interview prep, synthesis) and with generic research skills, so conflict risk remains.	2 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (517 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/discovery-process/SKILL.md
Commit: 9971018

Reviewed: 3 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.