Docs/readme powered by dailybot#3
Merged
Merged
Conversation
…ds generator) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…ostic) Add a third opt-in addon, dependency-upgrade, that teaches an agent to safely upgrade a repo's dependencies by reasoning about the repo's ACTUAL package manager (npm/pnpm/yarn + ncu, pip/poetry/uv/pipenv, cargo, go mod, bundler, composer) rather than assuming npm. The flow detects the manager from real manifests/lockfiles, classifies upgrades by semver, upgrades in safe batches, runs the repo's real validation gate after each batch, reverts a failing batch, and summarizes — never auto-committing. - addons/dependency-upgrade/SKILL.md: onboarding hook + flow - addons/dependency-upgrade/SPEC.md: RFC-2119 contract (detection, semver classification, batched upgrade, validate-after-each-batch gate, revert on failure, reconcile-don't-clobber, /lib-upgrade hook, validation) - templates/ecosystems.md: per-ecosystem detect/classify/upgrade/install/ gate/revert reference table - templates/upgrade-report.md: report shape - templates/lib-upgrade-command.md: /lib-upgrade delegator installed into a target repo's .agents/commands/ only when the addon is accepted - addons/README.md + onboard/SKILL.md Phase 7b: enumerate the new addon (recommend in trust mode only with a lockfile; never auto-install) Generalized from the website repo's legacy npm-only library-upgrade GUIDE. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
… failed validate-frontmatter) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The dependency-upgrade addon (added in 595e6f7 with its roster entry in addons/README.md) was not yet listed in onboard Phase 7b. Add the third opt-in addon row plus a describing paragraph: package-manager agnostic, recommend in trust mode only when a lockfile is present, never auto-install for everyone, and install the /lib-upgrade delegator only when accepted. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PR: feat: author sub-skill + opt-in dependency-upgrade add-on
Repo:
DailybotHQ/deepworkplan-skillBase:
main← Head:docs/readme-powered-by-dailybotCreate: https://github.com/DailybotHQ/deepworkplan-skill/compare/main...docs/readme-powered-by-dailybot?expand=1
Title:
Summary
Adds two capabilities to the DeepWorkPlan skill so a repository that installs it can grow and maintain its own kit — instead of relying on bespoke, per-repo tooling:
deepworkplan-authorsub-skill — a standardized generator for skills, agents, and commands. It replaces the old in-repoagent_skills_generatorpattern with something that travels inside the skill, so every install gets it. Ships withSKILL_TEMPLATE.mdandAGENT_TEMPLATE.md, and theonboardflow now emitsskill-create/agent-createcommand templates that delegate to it.dependency-upgradeadd-on — package-manager-agnostic dependency maintenance that upgrades in validated, revertible batches. Backs the/lib-upgradecommand. IncludesSPEC.md, per-ecosystem notes, an upgrade-report template, and alib-upgradecommand template.onboardPhase 7b now enumerates it as an available add-on.Why
Surfaced while dogfooding DWP on the
deepworkplan-websiterepo: the website needed a way to (a) evolve its own skills/agents/commands and (b) keep dependencies current, without copying logic into the repo. Promoting both into the skill keeps them reusable for any adopter and avoids vendored drift.Commits
f0df2c6deepworkplan-authorsub-skill (skills/agents/commands generator)595e6f7dependency-upgradeadd-on (package-manager agnostic)25ca48cname(was U+2011, failedvalidate-frontmatter)e98e830dependency-upgradeadd-on in Phase 7bChanges
skills/deepworkplan/author/— new sub-skill:SKILL.md+templates/{SKILL_TEMPLATE,AGENT_TEMPLATE}.mdskills/deepworkplan/addons/dependency-upgrade/— new add-on:SKILL.md,SPEC.md,templates/{ecosystems,upgrade-report,lib-upgrade-command}.mdskills/deepworkplan/onboard/— Phase 7b enumerates the add-on; newcommand-templates/{skill-create,agent-create}.mdskills/deepworkplan/SKILL.md— Author intent row addedAGENTS.md,README.md,docs/SUB_SKILL_GUIDE.md,skills/deepworkplan/addons/README.md16 files, +811 / −7.
Validation
python3 scripts/validate-frontmatter.py→ OK, all 11 SKILL.mdbats tests/→ 16 passed (1 skip: codex on PATH)Follow-up
Once merged and released, the
deepworkplan-websiterepo can re-pinskills-lock.jsonto a version that contains these additions (it currently pins2.0.2, which predates them).🤖 Generated with Claude Code