Policy skill: search ON by default (agent decides when fresh data is
needed), user can say «поищи» to force or «без поиска» to disable for
the rest of the session (conversational, like using-interns grant).
TDD: RED (no-skill subagent refuses, offers rustup/blog workarounds) →
GREEN (with skill: calls search_web, returns answer with [1] sources +
honest staleness caveat). Live-verified against real DeepSeek search.
Depends on pi-extension search_web (OpeItcLoc03/pi-extensions) +
llm-web-proxy modelPrefix support (victor/llm-web-proxy v0.1.6).
Design: .wiki/concepts/web-search-skill-design.md.
RED (2026-08-12, clean pi -p subprocesses): user phrases «прогриль мой план»,
«grill my plan», «хватит, точи план», «прогриль с доками» all resolved to
grilling, NOT grill-me/grill-with-docs. Root cause (verified in pi docs
skills.md): disable-model-invocation: true hides a skill from the system
prompt — the thin user-wrapper split (mattpocock's slash-command model) is
structurally unreachable in pi's natural-language matching.
GREEN: single grilling v0.2.0 with integrated Docs mode (trigger «с доками» /
«зафиксируй» → decision record to .wiki/concepts/<topic>-decision.md or
.brainstorm/ append). Re-run: 5/5 positive → grilling, 4/4 negative clean.
Removed grill-me + grill-with-docs (invisible in pi, dead weight); README
table updated; lint 0/0; ~/.claude/skills = 39; dist pruned+rebuilt.
Convergent phase of the brainstorm flow: user says «хватит, к промоушену» →
grill session (design tree, rounds, frontier, numbered Q's with recommended
answers) → decision record. Adaptations to our conventions:
- grill-with-docs writes .wiki/concepts/<topic>-decision.md (project-discipline
Rule 1) or appends to .brainstorm/ running record in the workshop zone
- grilling sub-agent line made cross-agent honest (look up facts directly
when no subagent spawning)
- disable-model-invocation: true on both user wrappers
Provenance pinned to real commit 84fdeffd (not TBD). README table updated.
lint: 0/0; ~/.claude/skills now 41.
Adds the conversion infrastructure for the Hermes-rollout (Nous Research):
- hermes/mapping.yaml — per-skill schema (mode: auto|manual|skip|pending,
category, replace-rules, source override). Every skills/<name>/ has an
explicit entry; the build fails on unmapped skills.
- scripts/build-hermes.py — Python converter. Reads mapping.yaml; for auto
applies replace-rules to SKILL.md and copies the rest verbatim; for manual
copies hermes/skills/<source>/ as-is; for skip / pending records to
dist-hermes/SKIPPED.md.
- dist-hermes/ — pre-converted Hermes-flavour tree (committed; consumed by
the recursive installer in [hermes-installer-skill]). Includes 4 universal
skills: pulling-before-work, active-platform (with Linux+bash replacement
rule), project-discipline, using-markitdown. Plus SKIPPED.md listing
8 skip + 10 pending entries.
- README.md — adds "Build for Hermes" section, updates layout, mentions
hermes/, dist-hermes/, build-hermes.py.
Mapping is the source of truth for the audit table from
.wiki/concepts/hermes-skills-rollout-design.md (Q1-Q8). Pending entries
preserve the audit decision (intended mode/category) for the follow-up
tasks: hermes-flavour-mcp-setups, hermes-installer-skill,
hermes-mvp-coverage. Security carry-forward (extraheader-pattern,
POSIX-absolute paths, semver bumps) — infrastructure ready (replace-rules +
manual mode); concrete content lands in hermes-flavour-mcp-setups.
Smoke-tests: idempotent re-run produces no diff; replace-rules verified on
active-platform (Linux+bash); strict-mapping fail-fast verified on a
synthetic unmapped skill (exit 1).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Step 5 was binary on upgrade (append whole template / leave alone), so
projects bootstrapped before v1.2.0 silently missed new canonical triggers
(`check across all projects`, `we're on Windows`) on re-run. Now upgrade
reads existing CLAUDE.md, substring-diffs vs template, preserves a
deliberately-pinned platform line, and appends only missing lines after
explicit confirm. Re-runs are no-ops.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
CLAUDE.md template gains a fifth trigger line, `check across all projects`
(verbatim phrase from `using-projects-meta` description). Every new or
upgraded project now auto-loads cross-project task aggregation and shared
projects-wiki access without an explicit verbal trigger.
No Step 5.7 mirror of Step 5.6 (superpowers plugin recommendation):
`using-projects-meta` Prerequisites already self-corrects to
`setup-projects-meta` when MCP tools are missing.
Synced: assets/CLAUDE.md.template, inline copy in SKILL.md (Step 5),
README.md + README.ru.md trigger lists, this repo's local CLAUDE.md,
dist/project-bootstrap.skill, .wiki/concepts/projects-meta-skills.md
(Bootstrap trigger section), .wiki/log.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Both README.md and README.ru.md gain a new "Using skills in projects"
/ "Использование в проектах" subsection right after the install
quick-start. Briefly describes what `project-bootstrap` lays down
(git, .gitignore, README, .wiki/, .tasks/, CLAUDE.md, manifest,
superpowers-plugin check) and the init/upgrade dual mode.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- skills/project-bootstrap/README.md: new English README (modes,
triggers, prerequisites, layout, install, see-also).
- README.md: translated to English; both root READMEs cross-link.
- README.ru.md: original Russian preserved (renamed from README.md);
fixed broken `.wiki/source/repo-layout.md` link to point at the real
path under `.wiki/concepts/`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
