CtrlK
BlogDocsLog inGet started
Tessl Logo

021-problem-framing

Use when a problem or issue needs explicit framing before deeper analysis begins — establishing the Problem statement, Current state, Desired state, Stakeholders, and Success criteria. This should trigger when an issue's Problem Framing point of view needs evaluation, or when a maintainer directly asks to frame a problem before root-cause analysis, design, or planning begins. Part of Plinth Toolkit

67

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 instruction skill: a lean overview body with a clean single-reference progressive-disclosure design, concrete step-level guidance, and an explicit completeness checkpoint in its workflow. The main improvement opportunities are consolidating the restated framing-element lists and surfacing one worked example.

Suggestions

Consolidate the five framing elements, which currently appear in near-identical form in the intro, 'What is covered in this Skill?', 'Constraints', and 'Workflow' — stating them once fully and referring back elsewhere would trim tokens without losing information.

Include one compact worked example inline (a two-line vague input restated as a solution-free problem frame) so the 'separate the problem from any solution' step has a concrete model before the reader jumps to the reference.

Add an explicit verification cue to Workflow step 5, e.g. re-checking each of the five fields against the MUST constraints before reporting, turning the flag-open-fields checkpoint into a true validate-then-report loop.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and explains nothing the model doesn't already know. It stops short of 5 because the five framing elements are restated across 'What is covered in this Skill?', 'Constraints', and 'Workflow' — a trimming opportunity — though each restatement serves a distinct function (coverage, MUST/MUST NOT rules, procedure), keeping it above anchor 3.

4 / 5

Actionability

For an instruction-only skill, the guidance is concrete and executable: 'Strip out wording that already assumes a fix, technology, or implementation, and restate the gap in observable terms' gives specific operations for each step. Not 5 because no worked example appears inline (they live in the reference), leaving minor gaps in covering common cases.

4 / 5

Workflow Clarity

The five-step sequence is clearly ordered, begins with reading the required reference, and includes a completeness checkpoint ('flag any field left open pending a clarifying answer'). Not 5 because there is no explicit validate-and-retry feedback loop; well above 3 because the checkpoint is explicit rather than implicit. No destructive or batch operations, so the validation cap does not apply.

4 / 5

Progressive Disclosure

The short SKILL.md body is a clean overview that moves all detailed guidance, examples, and constraints into a single well-signaled, one-level-deep reference (linked twice as a MUST-read constraint and in a dedicated 'Reference' section, and the file exists in the bundle). This matches the top anchor: clear overview, appropriately split content, easy navigation.

5 / 5

Total

17

/

20

Passed

Description

83%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 that clearly states both its function and its triggers, with concrete, domain-specific language throughout. Its weaknesses are minor: a slightly jargon-heavy trigger clause, some missing natural synonyms, and a toolkit tag that does nothing for discriminability.

DimensionReasoningScore

Specificity

The description names its domain and five concrete artifacts ('establishing the Problem statement, Current state, Desired state, Stakeholders, and Success criteria'), matching the anchor for several specific items with minor coverage gaps. It falls short of 5 because it describes a single framing action and its outputs rather than multiple distinct concrete operations.

4 / 5

Completeness

It explicitly answers both 'what' (establishing the five framing artifacts) and 'when' with two concrete trigger phrases ('Use when a problem or issue needs explicit framing...', 'when a maintainer directly asks to frame a problem before root-cause analysis, design, or planning begins'). This clearly matches the top anchor rather than 4, where 'when' would only be adequate.

5 / 5

Trigger Term Quality

Good natural keyword coverage — 'frame a problem', 'before root-cause analysis, design, or planning begins' — with only a few common variants missing (e.g., 'problem statement', 'define the problem'). Not 3, since the terms present are natural and varied rather than generic; not 5, since synonym coverage is incomplete and 'Problem Framing point of view needs evaluation' is jargon-heavy.

4 / 5

Distinctiveness Conflict Risk

The framing-before-analysis niche is mostly distinct, with explicit boundary markers ('before root-cause analysis, design, or planning begins') separating it from adjacent analysis skills. Minor overlap risk remains with those closely related skills, and 'Part of Plinth Toolkit' adds no discrimination, so it does not reach the clear-niche anchor of 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jabrena/plinth
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.