kramme-cc-workflow/skills/kramme:research/SKILL.md
Investigates a question against primary sources and saves one cited Markdown artifact. Use for reading legwork: official docs/API facts, source-code or spec checks, standards, and first-party service behavior before planning or implementation. Not for making product or architecture decisions, implementing code, broad web search, secondary blog summaries, or uncited answers.
npx skillsauth add abildtoft/kramme-cc-workflow kramme:researchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Investigate a bounded question against primary sources and preserve the answer as a cited Markdown artifact. The skill gathers source-backed facts; it does not decide what to build.
Arguments: "$ARGUMENTS"
Establish the research question
$ARGUMENTS as the research question after removing supported options.--output <path> as an explicit artifact path.Resolve the artifact path
<slug> from the question by lowercasing it, replacing each run of non-alphanumeric characters with one hyphen, trimming leading and trailing hyphens, and limiting it to 80 characters. If the slug is empty, use research.--output <path> is provided, store it as the candidate path. Otherwise inspect the workspace for an existing research-note convention, such as .context/research/, docs/research/, research/, or similarly named prior research Markdown files. Use the clearest existing convention..context/research/<slug>.md as the candidate path.<slug>-2.md, or abort.Identify acceptable sources
Investigate with claim-to-source traceability
UNVERIFIED or omit them.Write the cited Markdown artifact
# Research: <question>
## Question
<bounded question being answered>
## Scope
- Included: <what was researched>
- Excluded: <adjacent areas intentionally not researched>
## Sources
- <source title or path> — <URL/path and why this is primary>
## Findings
1. <source-backed finding with citation>
2. <source-backed finding with citation>
## Conflicts And Gaps
- <conflicting source, inaccessible source, or UNVERIFIED item>
## Non-Decisions
- <decisions this research does not make>
Report completion
| Condition | Response | | --- | --- | | Missing question | Ask for one bounded research question. | | Output path cannot be written | Stop with the exact path and filesystem issue. | | Output path resolves outside the working tree | Warn with the exact resolved path and write only after explicit confirmation. | | Output path already exists | Ask whether to overwrite, refresh, choose a suffixed path, or abort. | | No primary source access | Ask for source material or permission to write a gap-only artifact. | | Only secondary sources found | Use them only to locate primary sources; otherwise record the gap. | | User asks for a decision | Provide source-backed facts and explicit non-decisions; route decision-making to the relevant planning workflow. |
tools
Requires Linear MCP. Implements one Linear issue end to end, selects applicable code-review, convention, and PR-refactor gates, runs them to bounded convergence, verifies, and optionally opens the PR and iterates on CI and review feedback until green. Use when the user wants a single Linear issue taken from implementation through a clean Pull Request. Not for implementation-only work, SIW-tracked issues, stacked PRs, existing PR updates, or post-merge rollout.
development
Reviews PR and local changes for convention drift and overcaution against documented rules and mined peer-file practice. Use for new patterns, dependencies, abstractions, or defensive complexity that departs from established practice; every finding cites evidence. Supports --inline. Not for general code quality (use kramme:pr:code-review) or spec review (use kramme:siw:spec-audit --team).
testing
Charts huge or foggy initiatives into a local `.context` decision map and resolves one typed frontier ticket per session until the work is ready for SIW or another execution workflow. Use when the route to a destination cannot fit in one agent session or parallel workspaces need coordinated planning state. Not for clear specs, ordinary issue decomposition, implementation, or Linear-native tracking.
development
Builds a clearly throwaway logic/state or UI prototype to answer one design question before implementation hardens. Use when the user wants to sanity-check a state model, data shape, API surface, page layout, component direction, or interaction idea with disposable code. Not for production implementation, polished demos, visual diff reports, permanent routes, or broad design-system work.