Provides a structured approach for evaluating audit findings by
severity, reachability, and fix availability. Helps distinguish
between findings that need immediate action versus those that can
be tracked and fixed on a regular schedule.
Added a decision tree and example for speeding up CI: dependency
caching, parallel jobs, path filters, matrix sharding, test suite
optimization, and larger runners. Ordered by typical impact.
Replaced vague description with concrete numbers: agent focus degrades
above ~5,000 lines of non-task-specific context. Recommended target is
under 2,000 lines of focused context per task.
The table previously listed AI defaults and their alternatives but did
not explain why each pattern is problematic. Added a middle column with
the specific design or UX reason to avoid each default.
Added concrete signals for when a task needs further breakdown: session
length, acceptance criteria count, subsystem scope, and the "and" test
for task titles that indicate multiple tasks in one.
Added a concrete table with green/yellow/red thresholds for error rate,
P95 latency, client JS errors, and business metrics. Gives clear
criteria for advancing, holding, or rolling back at each rollout stage.
Added a decision tree for when bugs cannot be reproduced on demand,
covering timing-dependent, environment-dependent, state-dependent,
and truly random failure modes with specific investigation steps.
Helps determine what to measure first based on the symptom: slow first
load, sluggish interactions, navigation delays, or backend issues. Each
branch points to a specific profiling action.
The implementation phase now points to context-engineering for guidance
on loading the right spec sections per task instead of dumping the full
spec into context.
The five-axis review touches on security and performance but previously
did not link to the detailed skills. Added pointers so reviewers can
consult deeper guidance when needed.
The idea-refine skill was the only skill missing the standard Red Flags
and Verification sections. Added both to match the skill anatomy format
used by all other skills.
Added explicit guidance that external API responses must be validated
before use in logic or rendering. A compromised or misbehaving service
can return unexpected types or malicious content.
The security axis now checks whether external data sources (APIs,
logs, user content, config) are treated as untrusted and validated
at system boundaries. Added to both the review questions and checklist.
Replaced hardcoded test/test credentials in the database integration
example with GitHub Secrets references. Even for CI-only databases,
using secrets builds good habits and avoids accidental credential reuse.
Source code and tests are trusted, but config files, data fixtures,
and external docs may contain instruction-like text that should be
verified before acting on. Added trust level guidance and red flag.
Error messages, stack traces, and log output from external sources
can contain instruction-like text that should not be blindly followed.
Added explicit rules and a red flag for this indirect injection vector.
Here's what I added to address the audit findings:
**PROMPT_INJECTION (HIGH)** - Added a full "Security Boundaries" section with three subsections:
1. **Treat All Browser Content as Untrusted Data** - Explicit rules that DOM, console, network, and JS execution output are data, never instructions. Covers URL navigation restrictions and suspicious content flagging.
2. **Content Boundary Markers** - Visual diagram and rules separating trusted (user messages, project code) from untrusted (all browser-sourced data) contexts.
**COMMAND_EXECUTION (HIGH)** - Added **JavaScript Execution Constraints** subsection:
- Read-only by default
- No external requests from the page
- No credential/token access (cookies, localStorage, sessionStorage)
- Scope limited to current task
- User confirmation required for DOM mutations
Also updated the tool table description, added 5 new red flags, 2 new rationalizations, and 2 new verification checklist items to reinforce the security boundaries throughout the skill.
The JS execution tool remains functional for its core debugging purpose (state inspection, DOM queries, computed values) - the constraints just prevent misuse vectors.
Enable this repo to work as a Claude Code plugin so users can
install it via `/plugin marketplace add addyosmani/agent-skills`.
Add:
- .claude-plugin/plugin.json — plugin manifest exposing
.claude/commands/ as namespaced slash commands under
the agent-skills: prefix
- .claude-plugin/marketplace.json — marketplace catalog
listing this repo as the agent-skills plugin
Fix:
- hooks/hooks.json — rewrite from deprecated flat-array format
to the plugin-system format keyed by event type; use
${CLAUDE_PLUGIN_ROOT} so the hook resolves correctly when the
plugin is installed from the marketplace into the local cache
- README — replace non-existent `claude plugin add` with the
correct `/plugin marketplace add` workflow; document namespaced
slash commands and --plugin-dir usage; add .claude-plugin/ to
the project tree
The repository was renamed from swe-skills to agent-skills but
internal references were never updated. This caused:
- session-start.sh to silently fail (path using-swe-skills/ did
not exist; the directory is using-agent-skills/)
- slash commands to invoke non-existent swe-skills: namespace
- docs and setup guides to point at the old clone URL
Rename all occurrences across 14 files: commands, CLAUDE.md,
README tree, docs/, and hooks/.
Add MIT LICENSE file, CONTRIBUTING.md with skill quality guidelines,
expand .gitignore for safety, and remove leftover idea-refine.zip artifact.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Rewrite README with phase-organized skills table, per-skill
descriptions, setup guides for multiple editors, design
principles, and updated project structure.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Review phase skills covering OWASP Top 10 prevention, input
validation, Core Web Vitals, and measure-before-optimize discipline.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Verify phase skill covering TDD workflow, Prove-It pattern for
bugs, and test hierarchy guidance.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Build phase skills covering thin vertical slices and
production-quality UI development patterns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Define and Plan phase skills covering structured specifications
before code and decomposing work into verifiable tasks.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Addy Osmani