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.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured description with a clear 'Use when' clause that covers both what the skill does and when to invoke it. The trigger terms are comprehensive and natural, covering multiple coding task types. The main weakness is that the core capabilities ('frames', 'intent capture', 'drift monitoring') are somewhat abstract and could benefit from more concrete action descriptions.
Suggestions
Make the capabilities more concrete by specifying actions, e.g., 'Captures session goals upfront, tracks task scope against original intent, and flags when work drifts from the stated plan' instead of the more abstract 'intent capture and drift monitoring'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (coding-agent work sessions) and some actions (intent capture, drift monitoring), but the actions are somewhat abstract rather than concrete. 'Frames' and 'drift monitoring' are conceptual rather than specific operations like 'creates a session plan' or 'alerts when scope changes'. | 2 / 3 |
Completeness | Clearly answers both what ('frames coding-agent work sessions with explicit intent capture and drift monitoring') and when ('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') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would encounter: 'coding tasks', 'refactors', 'feature builds', 'bug fixes', 'multi-step execution', 'scope drift', 'planning', 'implementation'. These are terms a user or Claude would naturally associate with needing session framing. | 3 / 3 |
Distinctiveness Conflict Risk | This occupies a clear niche — session framing and drift monitoring for coding agents — that is unlikely to conflict with typical coding, planning, or project management skills. The combination of 'intent capture', 'drift monitoring', and 'session transitions' creates a distinct trigger profile. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent actionability and workflow clarity — the three-phase process with concrete templates and explicit checkpoints is strong. The main weaknesses are moderate verbosity in the CLI integration and interoperability sections, which explain pipeline mechanics and conceptual distinctions that could be more concise or split into reference files. Overall it's a solid, usable skill that could benefit from trimming supplementary context.
Suggestions
Move the 'How intent frames become learning signals' subsection and the detailed 'Relationship with context-surfing' explanation into a separate INTEROP.md or REFERENCE.md file, keeping only a brief summary and link in the main skill.
Tighten the Entire CLI Integration section — the fallback behavior and detection logic could be condensed to 3-4 lines since Claude can infer the 'continue silently' pattern.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some sections that could be tightened. The 'Entire CLI Integration' section explaining how intent frames become learning signals is somewhat verbose and explains pipeline mechanics Claude doesn't need spelled out. The 'Relationship with context-surfing' section also over-explains the conceptual distinction between scope drift and context quality drift. | 2 / 3 |
Actionability | The skill provides concrete, copy-paste-ready markdown templates for Intent Frame, Intent Check, and Intent Resolution blocks. It gives specific trigger cues, exact confirmation prompts to use, and clear drift detection examples. The workflow is fully executable as described. | 3 / 3 |
Workflow Clarity | The three-phase workflow (Capture → Monitor → Resolution) is clearly sequenced with explicit validation checkpoints: user confirmation before proceeding in Phase 1, drift checks at natural boundaries in Phase 2, and structured resolution in Phase 3. Multi-intent session rules provide clear sequencing and error recovery (resolve before opening new frame, handle pivots explicitly). The precedence rule for simultaneous skill firing is a thoughtful validation checkpoint. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's somewhat monolithic — the Entire CLI integration details, learning signal pipeline explanation, and interoperability section could be split into separate reference files. The interoperability section in particular is lengthy inline content that could be a linked reference. | 2 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- pskoett/pskoett-ai-skills
- Commit
fe0da1c
- 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.