3314112bb9
Add two new sources with summaries, new concepts (developer-as-agent-manager, review-is-the-new-bottleneck), new entities (SWEPR, Nikolai Sheiko), and a query on the Stanford source; update related concept pages, overview, index, and log.
4.3 KiB
Solve First, Then Skill-ify
#concept
Summary
The core method both HR interviews teach: don't build a skill speculatively — solve the task with the AI once, correct it until the output is right, then say "now create a skill from this." The skill freezes a proven workflow, not a guess about one.
Current Understanding
The recurring beginner mistake is writing the skill first and then trying to "shove it somewhere." The working loop is: do your real task through the AI → watch the result → correct it → freeze the final state into a reusable skill. Two trigger heuristics exist in the corpus:
- Eugene: turn any correction loop longer than ~3 messages into a skill.
- Konstantin: auto-create a skill after >5 tool calls on a task (the hermes curator variant).
The payoff goes beyond reuse: a packaged skill is a handoff and de-risking asset — "a person with not even a third of your HR experience can deliver a decent result," which cuts onboarding and lets the expert take a vacation. This is how skills-as-memory gets populated in practice — the method side of that architecture, and the fix for "don't teach the AI abstractly."
Agentic Evolution — the strongest formulation, plus the missing verification step (added 2026-07-30). nikolai-sheiko frames the same method as onboarding an employee: asking the expert "how do you do this?" yields theory; instead take the new employee (the agent) by the hand through hard real tasks, show it the rakes, then say: "remember all of this and write the manual for the next one." Without this you live on defaults; with it "vertical growth begins." He then adds what the corpus's earlier heuristics lacked — a verification protocol for the frozen skill:
- Write the skill together with the agent.
- Don't go to lunch.
- Launch a subagent with no context — it must solve the same task from scratch using only the skill.
- The main agent watches what fails and fixes the skill.
- The mentor agent thus onboards the next agent.
This is the first source to describe actually running something close to the skills falsification test proposed on skills-as-memory (same task, with-skill vs from-scratch) — though it tests the skill's completeness for one task, not whether the skill beats no-skill. His do-tomorrow extension: a skill that analyses your own sessions daily, automated via schedules/routines — evolution as a standing loop rather than a one-time freeze.
Evidence
- "You first solve a task with Claude; the moment you reach the final solution, you say — now create a skill from this"; ~3-message heuristic — 2026-07-14-yulia-interview.
- Do-the-task-then-freeze framing; skill-as-handoff to a junior hire; vacation/de-risking angle — 2026-07-14-nina-interview.
-
5-tool-calls auto-creation heuristic and curator pruning — 2026-07-14-skills-based-on-git.
- Skills prescribed specifically as the workaround for cross-session memory loss, and as the constraint on drift — 2026-07-21-larysa-interview.
- Agentic Evolution (walk the agent through tasks → have it write the manual); the context-free-subagent verification protocol; session-analysis skill as a daily loop — 2026-07-30-rakes-in-ai-sdlc-adoption.
Related Pages
- Concepts: skills-as-memory (the architecture this method feeds), levels-of-ai-usage (skills are the top practical rung), personal-ai-operating-system, leave-less-room-for-imagination (why a proven spec beats a written-ahead one)
- Entities: eugene, nina, konstantin, larysa, nikolai-sheiko
Contradictions / Uncertainty
- Whether the resulting skill is personal IP or employer work product is unresolved (Eugene vs sebastian) — 2026-07-14-nina-interview.
Next Questions
- What does a good "create a skill from this" prompt look like — does the corpus contain a concrete example transcript? (Partially answered 2026-07-30: Sheiko's "remember all of this and write the manual for the next one" after a guided run is the best prompt-shape the corpus has.)
- How do the ~3-message and >5-tool-call heuristics compare in practice; is one strictly better for non-programmers?
- Does the context-free-subagent check catch skill quality, or only completeness for the one task it was frozen from?