problem-framing-canvas

Guide teams through MITRE's Problem Framing Canvas. Use when you need a clearer problem statement before jumping to solutions.

Quality

76%

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 ./skills/problem-framing-canvas/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 delivers a well-sequenced, highly actionable interactive workflow with explicit checkpoints, but it is verbose with duplication and a leftover placeholder, and it relies on references to bundle files that are not actually present. Splitting inline material into the referenced files would resolve the main weakness.

Suggestions

Remove the verbatim restatement of the intent in the Purpose section and the leftover "Dean's Work" placeholder to tighten token use.

Actually create template.md and examples/sample.md (or drop the dangling references) so progressive disclosure resolves to real files instead of inline monolithic content.

Move the full output template (the fenced markdown block) into template.md and keep only a pointer in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly structured but padded: the Purpose section restates the frontmatter intent verbatim, and a leftover placeholder ("[If Dean has problem framing resources, link here]") plus inline enumerated options and pitfalls could be tightened; it does not reach the lean level-3 anchor.	2 / 3
Actionability	For an instruction-only facilitation skill it provides exact agent prompts, numbered enumerated response options, and copy-paste-ready output templates with worked SaaS onboarding examples, giving concrete actionable guidance.	3 / 3
Workflow Clarity	The three-phase process is explicitly sequenced (Step 0 context, then Phase 1/2/3 across eight numbered questions) with user-approval checkpoints ("Does this restatement capture the core problem? Should we refine it?") and clear feedback loops.	3 / 3
Progressive Disclosure	There is clear section structure, but the full output template and question banks sit inline in a single ~478-line file and the referenced template.md and examples/sample.md do not exist as bundle files, leaving signaled references dangling rather than cleanly one level deep.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 and a distinct niche, but its action list is thin and its natural-language trigger coverage could be broader. It is solid but not exemplary on specificity and trigger terms.

Suggestions

Expand the action list beyond "guide teams through" to name concrete outputs (e.g., generate a reframed problem statement and a How Might We question).

Add more natural user phrasings to the Use-when clause, such as "reframe", "validate the problem", or "we're solving the wrong problem".

Dimension	Reasoning	Score
Specificity	Names the domain ("MITRE's Problem Framing Canvas") and a guiding action, but only lists one action rather than multiple specific concrete actions, so it does not reach the level-3 anchor.	2 / 3
Completeness	It states what it does ("Guide teams through MITRE's Problem Framing Canvas") and gives an explicit "Use when you need a clearer problem statement before jumping to solutions" trigger, satisfying both what and when.	3 / 3
Trigger Term Quality	Relevant terms like "problem statement" and "jumping to solutions" appear, but coverage of natural user phrasings is limited and leans on the domain-specific canvas name, missing common variations.	2 / 3
Distinctiveness Conflict Risk	The MITRE Problem Framing Canvas niche with its "before jumping to solutions" trigger is a clear, distinct entry point unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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 suspicious	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/problem-framing-canvas/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.