CtrlK
BlogDocsLog inGet started
Tessl Logo

intent-framed-agent

Frames coding-agent work sessions with explicit intent capture and drift monitoring. Use when a session transitions from planning/Q&A to implementation for coding tasks, refactors, feature builds, bug fixes, or other multi-step execution where scope drift is a risk.

61

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/intent-framed-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The body is a clear, actionable instruction skill: concrete templates, an explicit three-phase workflow with a drift-check validation loop, and clean section structure. Its main weakness is conciseness, where the interop and integration sections over-explain concepts Claude already knows.

Suggestions

Trim the Entire CLI integration and context-surfing precedence/cadence sections to the essential rules; drop explanatory framing Claude already knows, which would lift conciseness toward 4-5.

Consider moving the context-surfing relationship detail into a short reference note so the core workflow stays lean.

Add one explicit 'if drift check is ambiguous, re-read the active intent frame before deciding' recovery loop to push workflow_clarity toward 5.

DimensionReasoningScore

Conciseness

Mostly efficient with templates and bullets instead of prose, but the Entire CLI integration and the context-surfing comparison/precedence discussion add conceptual material Claude largely already knows.

3 / 5

Actionability

Provides copy-paste-ready markdown templates with exact block headers and fields, plus specific rules; minor gaps come from subjective drift cues ('feels tangential').

4 / 5

Workflow Clarity

Clear three-phase sequence (Capture -> Monitor -> Resolution) with an embedded drift-check feedback loop and Multi-Intent recovery rules; not a 5 because there is no explicit error-recovery loop beyond pivot handling.

4 / 5

Progressive Disclosure

Single well-organized file with clear section headers and no bundle files; the Entire CLI and context-surfing sections could arguably be split out but the inlining is not excessive.

4 / 5

Total

15

/

20

Passed

Description

75%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.

The description is well-formed: it states a clear purpose, names concrete actions, and includes an explicit 'Use when' trigger clause with natural user-facing terminology. It is specific and distinct, just short of the most comprehensive examples which use multiple distinct trigger phrases and synonyms.

Suggestions

Add a few synonyms/common variations to the trigger clause (e.g., 'go ahead', 'let's start building') to lift trigger_term_quality and completeness toward 5.

Tighten 'Frames' to a more concrete action verb (e.g., 'Captures intent and monitors scope drift') to sharpen specificity.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions (intent capture, drift monitoring, scope-drift watching) rather than abstract language, though 'frames' is slightly soft and coverage is not fully comprehensive.

4 / 5

Completeness

Clearly states what the skill does and gives an explicit 'Use when' clause for when to apply it; not a 5 because the trigger is a single combined clause rather than multiple concrete trigger phrases.

4 / 5

Trigger Term Quality

Strong natural trigger phrasing ('refactors', 'feature builds', 'bug fixes', 'multi-step execution') that users genuinely say, but missing some synonyms and variations.

4 / 5

Distinctiveness Conflict Risk

Targets a distinct niche (planning-to-execution transition with scope-drift monitoring) with specific trigger context, with only minor overlap risk from the broad 'multi-step execution' phrasing.

4 / 5

Total

16

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pskoett/pskoett-ai-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.