ClaudeDo/docs/superpowers/specs/2026-07-03-session-skills-design.md

Session Skills — Design

Date: 2026-07-03 Status: Approved (design), implementation not started

Problem

Mika wants to give headless task agents a specific Claude skill (e.g. ponytail) without installing it globally in ~/.claude/skills/, where it would leak into every interactive session. Skills should be a first-class, per-level session setting alongside model, max_turns, and system_prompt — configurable global / per-list / per-task — and sourced from a GitHub URL.

Key facts that shape the design

• The Claude CLI discovers skills from two places: the global ~/.claude/skills/ (every session — undesirable here) and the working directory's .claude/skills/ (plus plugins). ClaudeDo fully controls each spawned session's WorkingDirectory (ClaudeProcess.cs:30), so a skill dropped into the session cwd is scoped to exactly that headless run.
• Auto-commit uses git add -A (WorktreeManager.CommitIfChangedAsync → _git.AddAllAsync, WorktreeManager.cs:142). Anything seeded into a worktree's .claude/skills/ would be committed unless explicitly excluded → the seeder must add the seeded paths to the worktree's info/exclude.
• A skill is not just prompt text: SKILL.md may reference scripts that run via Bash. Headless agents run with --permission-mode auto (effectively unattended), so a skill pulled from an arbitrary URL is unattended third-party code execution. This is why install is a deliberate, pinned, reviewable step — not a live per-run URL fetch.

Decisions (locked)

1. Install-and-pin, not live fetch. A dedicated registry screen installs a skill once: clone the repo, pin to the current commit, store locally. Per-level config then references installed skills by name (checkboxes), never a URL.
2. Three levels, additive union. Effective skill set = global ∪ list ∪ task. (Unlike model/prompt, which override — skills add up. Trade-off accepted: an inherited skill can't be switched off for a single task in the MVP.)
3. One repo = one skill. Installer accepts only a repo with SKILL.md at the root (covers ponytail). Multi-skill repos / plugin-format repos are out of scope for MVP.
4. Public repos only (plain git clone over HTTPS, no auth) for MVP.

Architecture

Storage & registry

• Installed skills live at ~/.todo-app/session-skills/<name>/ (the cloned repo contents, SKILL.md at root).
• New DB table session_skills: name (PK), source_url, pinned_ref (commit SHA), description, added_at.
• New worker service SessionSkillRegistry (in a new Skills/ area under the Worker):
  • InstallAsync(url) — clone to temp → validate SKILL.md at root → parse frontmatter (name, description) → resolve HEAD SHA as pinned_ref → move into place → upsert DB row. Name collision → error surfaced to UI. The clone step is injected (IRepoCloner) so tests use a local source dir — no real network, no real CLI.
  • UpdateAsync(name) — re-fetch, checkout latest, refresh files + pinned_ref.
  • RemoveAsync(name) — delete dir + row.
  • ListAsync() — registry entries for the UI.

Resolution

TaskRunner.ResolveConfigAsync (TaskRunner.cs:488) already merges task → list → global for the other fields. Add:

SkillNames = Union(task.SessionSkills, listConfig?.SessionSkills, global.SessionSkills)

deduped, filtered to names that still exist in the registry (a removed skill is silently dropped — logged). Add IReadOnlyList<string> SkillNames to ClaudeRunConfig (ClaudeArgsBuilder.cs:5). No CLI flag is emitted — skills are seeded on disk, not passed as args. ClaudeArgsBuilder.Build is unchanged for skills.

Per-level storage: a nullable TEXT column session_skills (JSON array of names) on tasks, list_config, and app_settings.

Seeding

New service SessionSkillSeeder, called by TaskRunner after the working dir is resolved and before ClaudeProcess.RunAsync:

• For each resolved skill name, copy ~/.todo-app/session-skills/<name>/ → <cwd>/.claude/skills/<name>/ (overwrite → idempotent for resume/re-run).
• If the cwd is a git worktree, append /.claude/skills/<name>/ to the worktree's info/exclude (path via git rev-parse --git-path info/exclude, so it targets the per-worktree exclude), only if not already present. Only the seeded subdirs are excluded — never blanket-exclude /.claude/, in case the target project commits its own .claude/.
• Sandbox runs (not a repo) skip the exclude step.
• No separate cleanup: seeded dirs vanish with the worktree/sandbox.

allowedTools caveat

--allowedTools is only emitted when set (ClaudeArgsBuilder.cs:80); normal task runs leave it null → all tools allowed → the Skill tool is available. If a future per-task allowedTools restriction is added, it must include Skill. Noted, not handled in MVP.

UI

Mirror the existing agent-file pattern.

• Registry screen ("extra mask"): a new Skills tab in the Settings modal (SettingsModalView.axaml) with SessionSkillsSettingsTabViewModel. Lists installed skills (name, description, source, short ref); Add (URL text box → install), Update, Remove. Status/error line like FilesSettingsTabViewModel.
• Global selector: multi-select (checkbox list) of installed skills in the General settings tab → AppSettings.SessionSkills.
• List + Task selectors: add a skills multi-select to the shared AgentConfigEditor control (AgentConfigEditor.axaml / AgentConfigEditorViewModel.cs), which is already reused by both List settings and the per-task flyout — one addition covers both levels, with the existing inheritance-badge pattern.

Hub / client surface

New WorkerHub methods + IWorkerClient entries (update hand-rolled fakes in both test projects — see memory iworkerclient_fakes_sync): GetSessionSkills, InstallSessionSkill(url), UpdateSessionSkill(name), RemoveSessionSkill(name). Extend AppSettingsDto, ListConfigDto, UpdateListConfigDto, UpdateTaskAgentSettingsDto with the selected skill-name lists. New SessionSkillDto.

Edge cases

• Removed skill still referenced by a level → dropped at resolve time, logged, no failure.
• Name collision on install → reject with a clear message; offer Update instead.
• Repo without root SKILL.md → reject at install.
• Target project already has .claude/skills/ → additive copy; exclude only our subdirs.
• Resume / re-run reuses the worktree → re-seed overwrites, exclude append is idempotent.

Verification (must-check, can't be unit-tested)

• Does claude -p actually load and invoke a skill placed in cwd .claude/skills/? This is the load-bearing assumption. Manual smoke test with ponytail before calling the feature done. If headless mode does not surface cwd skills, fall back to CLAUDE_CONFIG_DIR isolation (heavier — needs credentials copied) and revisit.
• Seeded skill is not committed by the auto-commit step (worktree run).
• Skill does not appear in a normal interactive session (no global leak).

Out of scope (MVP)

Private-repo auth; multi-skill / plugin-format repos; auto-update & update notifications; per-task disabling of an inherited skill; surfacing skill invocation in the run log.