tekhne

Review .context/plans/*.md files using 3 independent subagent reviewers: Technical (feasibility, gaps, soundness), Strategic (scope, alignment, priority), and Risk (blind spots, edge cases, failure modes). The skill FIRST asks the user which models to assign to each reviewer -- presenting available options based on the user's environment (OpenCode Zen, OpenCode Go, a native Anthropic CLI harness, or BYOK). Each reviewer receives the same plan with a role-specific lens and returns structured feedback. The main agent consolidates all three perspectives. Triggers: 'review this plan', 'audit plan', 'plan review', 'check my plan', 'what's wrong with this plan', 'review all plans', 'plan quality check'. Do NOT use for plans not in .context/plans/, one-off notes, or external documents.

Safe-to-fail experiment for Complex domain problems where cause-effect is only visible in retrospect. Two-phase: foreground qualify → background probe → sense result. Use when: probe, safe-to-fail, test hypothesis, experiment with hypothesis, Complex domain with hypothesis. NOT for brainstorming (use brainstorm) or known cause-effect (use investigate).

Guide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences. Use when drafting professional messages, preparing meeting communications, or improving written communication.

Use when responding to questions or providing information requiring professional honesty and directness over excessive agreeableness.

Generate PromQL queries for calculating error rates, aggregating metrics across labels, creating histogram percentiles, writing recording rules, and building SLO burn-rate alerts following Prometheus best practices. Use when creating new PromQL queries, implementing monitoring and alerting rules, building observability dashboards, working with Prometheus metrics (counters, gauges, histograms, summaries), or applying RED (Rate, Errors, Duration) and USE (Utilization, Saturation, Errors) monitoring patterns.

Comprehensive toolkit for validating, optimizing, and understanding Prometheus Query Language (PromQL) queries. Use this skill when working with PromQL queries, prometheus queries, metrics queries, alerting rules, recording rules, or grafana dashboards to check syntax, detect anti-patterns, identify optimization opportunities, and interactively plan queries with users.

Captures and documents agent findings as verifiable artifacts — screenshots via agent-browser or playwright-mcp, captured logs, and script output. Use when completing investigations, audits, UI changes, infrastructure tasks, or any task where evidence of actions taken must be preserved.

Splits a large feature branch into smaller, focused pull requests using stacked branches and cherry-pick. Groups commits by concern (infrastructure, application logic, tests, housekeeping), proposes descriptive branch names for user approval, creates stacked branches, and generates What/Why MR titles and descriptions. Use when the user says a PR is too big, asks to split a PR, wants to decompose a branch, or needs to break work into reviewable chunks.

Generate an original, autobiographical confessional stand-up bit/story/monologue built from a genuinely painful personal anecdote, using techniques like multi-voice character embodiment (switching voice mid-story to become a parent/cop/friend/animal/younger-self), rhythmic escalating repetition, self-implicating honesty, vivid sensory specificity, plus a blunt closing truth in place of a tidy moral. Use it when a user wants to write, punch up, workshop, critique such a piece before it gets tested at an open mic. Do not use it for observational one-liners with no personal narrator, absurdist/surreal sketches, character-only sketch writing, requests to reproduce, quote, transcribe, imitate a real performer's actual routine.

Ensure Tessl plugins meet all requirements for public registry publication with comprehensive validation. Use when publishing skills to public registry, validating .tessl-plugin/plugin.json configuration, creating evaluation scenarios, checking quality thresholds (A-grade >=126/140 on the nine-dimension skill-quality-auditor scale), or preparing plugins for release. Validates eval scenario coverage, plugin.json fields (name, version, private, description, skills), agent-agnostic compliance, and publication readiness.

Search and analyze biomedical literature from PubMed using the free E-utilities API. Use when researching medical topics, discovering clinical papers, fetching article metadata by PMID, performing deep paper analysis, or downloading open-access PDFs from PubMed Central. Triggers: pubmed search, search biomedical literature, find medical papers, PMID lookup, pubmed metadata, clinical literature search, biomedical research, life sciences papers, PMC download, ncbi search.

Reproduce and verify the benchmark claims of a tool or paper already triaged in the research repo. Locates the benchmark harness, runs it, and records verified vs. reported figures in benchmarks/sources/{slug}-repro.md. Triggers: reproduce benchmark, verify claims, run benchmark, check benchmark, benchmark reproduction, verify numbers.

Reproduce and verify the benchmark claims of a tool or paper already triaged in the research repo. Locates the benchmark harness, runs it, and records verified vs. reported figures in benchmarks/sources/{slug}-repro.md. Triggers: reproduce benchmark, verify claims, run benchmark, check benchmark, benchmark reproduction, verify numbers.

Analyze collaboration patterns (HOW) and compute metrics from captured sessions. Use when reviewing collaboration quality, analyzing human-AI interaction, computing session metrics. Triggers include "retrospect collab", "collaboration analysis", "session patterns", "how am I collaborating".

Analyze domain insights (WHAT/WHY learned) from captured sessions. Use when reviewing learnings, extracting patterns, analyzing decisions. Triggers include "retrospect domain", "domain analysis", "what did I learn", "session insights".

Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise authors on what to address. Use when a user wants to review, validate, or quality-check an Agent Skill.

A skill with code blocks and imperative instructions for testing content and contamination analysis.

Maintain docs/RISK_REGISTER.md, the living, append-only list of every deferred item, interim shortcut, and open architecture decision for this project. Use when a shortcut is taken, a decision is postponed, a follow-up is filed, or an existing entry is actually resolved. DO NOT use for accepted, finalized architecture decisions (use adr-capture instead), for session-local working notes that don't need to survive across the team (use context-file / the local scratch-notes directory instead), or for anything that must stay confidential (the register is a committed, team-visible doc). Triggers: 'add to risk register', 'log this as a risk', 'track this shortcut', 'this is a known gap', 'mark risk #N resolved', 'what's on the risk register', 'what's still open'.

Generate an original, high-energy observational stand-up bit — a routine built on one bold contrastive claim ("there's a difference between X and Y") about society, relationships, race, gender, class, money, respectability politics, media hypocrisy — escalating through rhythmic repetition, rising volume, a voiced-then-defeated imagined objector, a sharpened recurring refrain, toward a tight, quotable, unhedged aphoristic closing line, in the tradition of Chris-Rock-style observational stand-up. Trigger on requests to write a stand-up bit, comedy routine, observational monologue with escalating examples building to a punchline. This skill is not for scripted sketch comedy, character-based sketches, mockumentary bits, confessional storytelling comedy, flat one-liner lists lacking escalation, or requests to reproduce a real comedian's actual material verbatim.

Manage project-level agent behavioural rules recorded in a single rules file. Use when the user says 'new rule', 'add a rule', 'record that', 'make a rule that', 'note this', 'take note of', 'new instruction', or asks to codify an agent directive. Read the rules file to check existing rules before adding a new one. DO NOT use for ephemeral notes, one-off instructions, or instructions that belong in the project's own agent-facing docs. Triggers: 'new rule', 'add a rule', 'record that', 'make a rule', 'codify this', 'rule about', 'create a directive', 'note this', 'take note of', 'new instruction'.