Help us improve
Share bugs, ideas, or general feedback.
From strikethroo
Refines an existing Strikethroo plan by resolving the plan ID, running project hooks, pressure-testing for gaps and contradictions, and updating the plan in-place.
npx claudepluginhub e0ipso/strikethrooHow this skill is triggered — by the user, by Claude, or both
Slash command
/strikethroo:st-refine-planThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Drive the end-to-end refinement of an existing Strikethroo plan. The skill
Creates a new Strikethroo plan for a repository: locates the project root, runs pre-plan hooks, gathers clarifications, allocates a plan ID, and writes a conformant Markdown plan.
Generates structured implementation plans from feature descriptions or requirements, grounded in repo patterns and research. Deepens existing plans via interactive sub-agent review.
Orchestrates parallel architecture and experience reviews of implementation plans, scores findings across dimensions like data flow and UX, consolidates ranked fixes for user approval and auto-application. Use after planning, before non-trivial coding.
Share bugs, ideas, or general feedback.
Drive the end-to-end refinement of an existing Strikethroo plan. The skill
is assistant-agnostic and self-contained: every script it invokes lives under
this skill's scripts/ directory and is referenced by relative path.
The user supplies the numeric plan ID conversationally, along with any optional refinement notes or constraints. Treat the plan ID as the only authoritative source of intent. Do not invent answers to clarifying questions — prompt the user instead.
Run scripts/find-strikethroo-root.cjs from the user's working directory.
The script walks up looking for .ai/strikethroo/.init-metadata.json and
prints the absolute path of the resolved root on success.
If the script exits non-zero, the working directory is not inside an
initialized strikethroo workspace. Stop and ask the user to run the project
initializer (e.g. npx strikethroo init) before continuing. Do
not attempt to refine a plan outside of a valid root.
For every subsequent step, treat the path printed by this script as <root>.
Run scripts/validate-plan-blueprint.cjs <plan-id> planFile to obtain the
absolute path of the plan file. The same script also accepts these field
names (single-field output mode) and exposes them on demand:
planDir — absolute path of the plan directorytaskCount — number of existing task files in that plan's tasks/blueprintExists — yes or notaskManagerRoot — absolute path of <root>planId — the resolved numeric plan IDIf the script exits non-zero, stop and ask the user to confirm the plan ID. Do not guess a different ID.
Read these files, in order:
<root>/config/STRIKETHROO.md — directory conventions and project context.<root>/config/hooks/PRE_PLAN.md — execute the instructions it contains
before proceeding.<root>/config/templates/PLAN_TEMPLATE.md — the structural baseline the
refined plan must continue to conform to.Read the entire plan end-to-end. Without modifying the file:
Document each gap with {section, issue, severity, proposed fix} so you can
reference it when refining the plan.
Default to Interactive Clarification. Only switch to Autonomous Clarification when the trigger is unambiguous and beyond reasonable doubt. Treat ambiguity as a vote for Interactive: asking a question the user cannot answer is recoverable; making silent assumptions when the user expected to be consulted is not.
Switch to Autonomous Clarification only if at least one of the following holds without interpretation:
st-full-workflow skill)
has declared autonomous operation for this invocation in the prompt
passed to this skill.st-full-workflow
orchestrator or by a caller that explicitly requests autonomous operation).If none of the above holds, use Interactive Clarification even when the user's presence is uncertain. Do not infer autonomous mode from indirect signals such as terse prompts, scripted-looking input, or absence of recent user messages.
After the clarification loop completes, append all new findings to the "Plan Clarifications" section in the plan document using the existing format (table with question/answer pairs). Mark the source of each entry appropriately.
Think harder before interrupting the user — only trigger this loop when you can cite concrete uncertainties.
Think harder before flagging gaps — only document concrete uncertainties you can cite.
Once you have sufficient context (or have documented all missing context), refine the plan directly in-place. The plan file path is the one returned by step 2.
id and directory. Do not create
a new plan ID. Do not move the plan to a new location.<root>/config/templates/PLAN_TEMPLATE.md. Add missing sections if
necessary.Notes with a clearly labeled section
so it remains discoverable.Notes section that briefly
states what changed in this refinement session (e.g.,
- 2025-03-16: Clarified auth flow tokens and updated architecture diagram).<root>/config/hooks/POST_PLAN.md to ensure
the refined plan still meets quality bars.Execute <root>/config/hooks/POST_PLAN.md after the plan file is updated.
Conclude with exactly this block as the final output:
---
Plan Refinement Summary:
- Plan ID: [numeric-id]
- Plan File: [absolute-path-to-plan-file]
The summary is consumed by downstream automation; keep the format exact.