Claude Skills by tkhribech

One or two sentences optimized for TRIGGERING — say when to use this skill, in the words a user would actually say, including the trigger phrases ("run the X", "check Y", "how are Z doing"). The harness matches requests against this line; a vague description means the skill never fires.

Use when the founder asks for a deep-research briefing ("deep research this", "give me a full read on X"), OR before any research-backed deliverable — a blog post, newsletter, landing-page claim, market read, or strategic bet — where multiple viewpoints and fact-checked claims matter. Runs a 4-phase pipeline — parallel expert lenses → contradiction map → synthesized briefing → adversarial peer review + primary-source verification of every citation. Overkill for a simple factual lookup.

Use PROACTIVELY the moment a task has many layers — multiple dependent steps, unknowns that could change the approach, debugging where the first theory might be wrong, or anything that needs verification before handoff. Also use when a task keeps failing or stalling, or when the founder says "slow down and do this right", "think this through first", or "use the five gates". Loads the five-gate task loop so the session applies the full working discipline.

Use at the end of any substantial working session — when the founder says "done for the day", "wrapping up", "let's close out", or when a long session ends with work in flight. Captures this session's corrections and decisions into the memory tree, writes the handoff file, updates pending tasks, and leaves the workspace clean for the next session's cold start.

Run the founder's weekly business review — pull the week's numbers, compare against the running baseline, surface what changed and what needs a decision. Use when the founder says "weekly review", "how did the week go", "run the numbers", or at the first session of a new week.