jordangunn
34 verified skills204 total stars
task-create
Create a new task directory with 00_TASK.md from template. Sets initial epistemic_state to candidate and lifecycle_state to inactive. Computes created_at via deterministic time script.
tools6
plan-exec
Execute an existing docs/planning/phase-N plan sequentially by completing lettered sub-plans and roman numeral tasks, appending Output and Handoff, and finishing with a root plan wrap-up.
documentation6
task-review
Review a task by updating last_reviewed_at timestamp. Recomputes derived status and flags any hash mismatches without changing epistemic state.
tools6
plan-create
Materialize the current conversation into a new docs/planning/phase-N plan (root plan plus sub-plans and task files).
documentation6
refactor-dictionaries
Audit dictionary usage against the Dictionary Usage Doctrine. Produces a severity-grouped report with minimal refactor suggestions.
development6
doctor
Orchestrator skill for the `doctor` skillset. A diagnostic protocol that models software failures as medical cases — preventing premature action, wrong-layer fixation, and false certainty in complex codebases.
development6
prompt-exec
Execute the forged prompt exactly as written, with no reinterpretation. Requires explicit user consent and a ready prompt artifact on disk. Deletes the canonical prompt after successful execution.
testing6
refactor-inline-complexity
Audit inline complexity and recommend variable extraction. Produces a report with flattening suggestions for nested expressions.
development6
task-invalidate
Invalidate a task by setting epistemic_state to invalidated. Requires a reason. Optionally sets superseded_by to point to a replacement task.
testing6
task-list
List tasks from a root directory with optional filters. Supports filtering by staleness, validation state, lifecycle state, and kind.
tools6
mimic
Persona overlay skill. Applies stylistic transforms to prose output. Slot: assets/persona/spec.yaml | Library: assets/library/ | Schema: assets/schema.yaml
development6
task-next
Navigate to the next task in chronological order. Returns the task ID after the specified task based on created_at timestamp.
testing6
prompt
Orchestrator skill for the `prompt` skillset. Dispatches to member skills in a safe, predictable order. Separates intent formation from execution to protect humans from premature or misaligned execution.
development6
md-split
Splits a Markdown file by H2 headings into numbered documents, generates .INDEX.md, and scaffolds .SUMMARY.md workflow.
documentation6
refactor-squatters
Detect squatters: modules and packages that occupy namespace positions they do not semantically own. Identifies utility dumps, stuttery siblings, axis violations, layer bleeding, and semantic diffusion — common structural smells introduced by agentic programming.
tools6
refactor-structural-duplication
Identify structurally duplicate logic (pipeline-spine duplication) across semantically distinct modules. Use when multiple implementations share the same orchestration skeleton (e.g., bounds→shape→chunking→reduction→wrap), and unification may require subtle abstraction. Produces a duplication map and a safe extraction/refactor plan.
development6
prompt-forge
Shape, refine, and stabilize human intent into a canonical prompt artifact without executing anything. Iteratively clarifies ambiguity and contradictions until the user explicitly confirms readiness.
testing6
refactor
Orchestrator skill for the `refactor` skillset. Dispatches to member skills for code quality audits and structural improvements.
development6
refactor-import-hygiene
Audit Python imports to preserve semantic context and prevent shadowing after refactors. Prefer namespace-first imports over direct symbol imports for generic identifiers.
development6
refactor-semantic-noise
Audit semantic noise and namespace integrity. Produces a severity-grouped report with namespace/rename suggestions.
development6
task-validate
Validate a task by setting epistemic_state to validated. Requires explicit validation info (who/why). Computes hash and updates last_reviewed_at.
testing6
doctor-intake
Convert the user's raw description into a clinically precise intake note suitable for handoff to another agent or human. Captures symptoms, normalizes terminology, and separates observation from belief.
tools6
task-activate
Activate a task by setting lifecycle_state to active. Refuses activation if task is invalidated, stale, or has hash mismatch without revalidation.
testing6
refactor-lexical-ontology
Audit identifiers and namespaces for lexical-semantic and ontological correctness. Detect semantic role misalignment (agent/tool/process/artifact), derivational misuse (e.g., -er agent nouns), and category errors between modules, packages, classes, functions, and data artifacts. Output a single Markdown report with actionable fixes.
tools6
doctor-triage
Perform breadth-first hypothesis surfacing and prioritization across all ownership zones, without commitment. This is not diagnosis and not investigation.
testing6
refactor-module-stutter
Detect module/package name stutter in Python public APIs. Produces a Markdown report and optional CI gate.
development6
doctor-exam
Conduct a focused, evidence-driven examination of ONE triaged suspect area. This is a test, not a verdict. Evidence may falsify the leading hypothesis.
testing6
doctor-treatment
Produce a treatment note that combines diagnosis, confidence, supporting evidence, alternative explanations, and proposed treatment options. Creates an artifact, not execution.
documentation6
md
Orchestrates markdown chunking workflows (split → index → summary)
tools6
plan
Orchestrator skill for the `plan` skillset. Dispatches to member skills in a safe, predictable order.
tools6
plan-status
Display the execution status of a plan by parsing frontmatter metadata. Shows progress at-a-glance without requiring manual inspection of each file.
data-ai6
task
Orchestrator skill for the `task` skillset. Standardizes task creation and lifecycle control with explicit validation, chronological awareness, and deterministic integrity.
testing6
task-status
Compute and display derived status for a task. Runs deterministic status computation and outputs summary of staleness, hash integrity, and eligibility.
tools6
task-prev
Navigate to the previous task in chronological order. Returns the task ID before the specified task based on created_at timestamp.
testing6