[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DB7SYM76G4W3F2AVWVFH8W":3,"skill-same:01M6DB7SYM76G4W3F2AVWVFH8W":97},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6DB7SYM76G4W3F2AVWVFH8W","competitive-programming-solver",null,"Solves algorithmic \u002F competitive-programming problems with fast, correct solutions in C, C++, and Python. Use whenever the user mentions Codeforces, AtCoder, LeetCode, Infoarena, pbinfo, Kattis, SPOJ, USACO, ICPC, IOI, or any online judge \u002F olympiad \u002F contest, or a statement with input\u002Foutput specs, time\u002Fmemory limits, \"TLE\", \"AC\", or \"competitive programming\". Trigger even for a buggy submission.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35],"programming","competitive programming solver","python","memory","fast","contest","correct","user","use","time","c++","trigger","2026-11-10 10:12:30",false,"---\nname: competitive-programming-solver\ndescription: Solves algorithmic \u002F competitive-programming problems with fast, correct solutions in C, C++, and Python. Use whenever the user mentions Codeforces, AtCoder, LeetCode, Infoarena, pbinfo, Kattis, SPOJ, USACO, ICPC, IOI, or any online judge \u002F olympiad \u002F contest, or a statement with input\u002Foutput specs, time\u002Fmemory limits, \"TLE\", \"AC\", or \"competitive programming\". Trigger even for a buggy submission.\n---\n\n# Competitive Programming Solver\n\nA skill for producing **correct and fast** solutions to algorithmic problems, in **C, C++, and Python**, across all major online judges.\n\nThe goal is not just to write code — it's to write code that **passes within the time limit on the judge's machine**, which is the only success criterion that actually matters in competitive programming.\n\n## When to use this skill\n\nUse whenever the user is solving a problem from an online judge or competition. Concrete triggers:\n\n- Names a judge: Codeforces, AtCoder, LeetCode, Infoarena, pbinfo, Kattis, SPOJ, USACO, HackerEarth, HackerRank, CSES, oj.uz, ICPC, IOI, etc.\n- Pastes a problem statement (input format, output format, constraints, time\u002Fmemory limits)\n- Shares an existing solution that gets TLE, WA, MLE, RE, or partial score\n- Asks for \"the fastest way to compute X\" with constraints like N ≤ 10^6\n- Talks about contests, olympiads, ranked rounds, or training\n\nIf the user is on **pbinfo.ro specifically and needs Python to pass within tight limits**, also load the companion skill `pbinfo-python-jit` — it adds shellcode JIT techniques specific to the pbinfo sandbox.\n\n## The five-phase workflow\n\nEvery problem follows the same phases. Do them in order, but don't skip ahead.\n\n### Phase 1: Understand the problem\n\nRead the statement carefully. Identify:\n\n- **What is asked**: one output, multiple queries, optimization, counting, decision?\n- **Input\u002Foutput format**: stdin\u002Fstdout, named files, special separators, multiple test cases?\n- **Constraints**: N, Q, values, time limit, memory limit, stack limit\n- **Edge cases**: N=1, all same, all distinct, max values, empty inputs\n\nFor pbinfo problems specifically: the I\u002FO is always named files (e.g. `problema.in` \u002F `problema.out`), not stdin\u002Fstdout.\n\nIf anything is unclear (especially the formula for \"type 2 queries\", the exact pairing convention \"ordered vs unordered\", or whether indices are 0- or 1-based), **ask the user** before writing code. Wrong formula = WA on all hard tests.\n\n### Phase 2: Pick the algorithm\n\nMatch the constraints to the algorithm class. This is the most important step.\n\n| N (or operations) | Allowed complexity (per second, C++) |\n|---|---|\n| ≤ 12 | O(N!) brute force \u002F bitmask |\n| ≤ 25 | O(2^N) meet in middle |\n| ≤ 500 | O(N^3) Floyd-Warshall, matrix DP |\n| ≤ 5000 | O(N^2) DP, edit distance |\n| ≤ 10^5 | O(N log N) sort, segment tree |\n| ≤ 10^6 | O(N) or O(N log log N) sieves, BFS, two pointers |\n| ≤ 10^7 | O(N) with low constant, mostly arithmetic |\n| ≤ 10^9 | O(log N) or O(√N) per query |\n\nPython is **5–20× slower** than C\u002FC++ depending on the workload. For Python plan for a constant of ~10×; if the C++ solution barely fits the time limit, Python likely needs an algorithmic shortcut or low-level tricks. See `references\u002Fpython-speed.md`.\n\nDocument the chosen algorithm briefly in a comment at the top of each source file, especially for Python. It helps debugging and helps the user understand.\n\n### Phase 3: Implement (C++ first)\n\n**Write C++ first**, even if the user wants Python. Reasons:\n1. Catches algorithm bugs quickly — C++ runs fast enough that you don't conflate \"slow\" with \"wrong\"\n2. Establishes the reference behavior against which Python \u002F C can be verified\n3. Most online judges run C++ at full speed, so this is the safest path to AC\n\nThe C++ template lives in `references\u002Ftemplates\u002Ftemplate.cpp`. Key features:\n- `FastScanner` class with `1 \u003C\u003C 20` byte buffer and inlined `readChar`\u002F`readInt`\n- `freopen` for named-file I\u002FO if the judge requires it\n- String-buffered output (`string out; out.reserve(Q*16); ... fwrite(...)`) — `printf` is too slow when Q is large\n- Avoid `std::endl` (flushes); use `'\\n'`\n- `using namespace std;` is fine for competitive programming\n\n### Phase 4: Implement C (if needed)\n\nSome judges accept only C (no C++). Some users want C for educational purposes. C is essentially C++ minus STL — port the C++ solution by replacing `vector` with raw `malloc`\u002F`free`, `string` with manual `char buf[]`, and `deque` with circular buffer arrays.\n\nTemplate: `references\u002Ftemplates\u002Ftemplate.c`.\n\n### Phase 5: Implement Python\n\nPython has two failure modes: **TLE** (algorithm is fine but pure Python overhead kills it) and **MLE** (allocating millions of Python int objects). Defenses:\n\n1. **Read in bulk** as bytes: `data = sys.stdin.buffer.read()`, parse with custom scanner over `bytes` (each byte is already an int 0–255, no decode needed)\n2. **Use `array.array`** (or `bytearray` for byte arrays) instead of lists for million-element numeric storage\n3. **Hoist locals**: in hot loops, `data = self.data; n = self.n; i = self.i` before the loop, write back at the end\n4. **Batch I\u002FO**: collect outputs in a list and `\"\\n\".join(out)` at the end; never `print(...)` in a loop with millions of iterations\n5. **Algorithmic shortcuts**: linear sieves, monotonic deques, sum-of-digit-parity via `sum(bytes(str(x), 'ascii')) & 1` (3× faster than `while x%10`)\n\nPython template: `references\u002Ftemplates\u002Ftemplate.py`. For deeper performance techniques and tricks specific to interpreted Python, see `references\u002Fpython-speed.md`.\n\nIf pure Python can't make the time limit and the user is on **pbinfo**, escalate to the companion skill `pbinfo-python-jit`, which uses shellcode-via-ctypes-mmap to run native x86-64 code from inside Python. It has consistently turned 35–65p Python solutions into 100p across a dozen problems.\n\n## Verification before submission\n\nFor every solution, before handing it to the user:\n\n1. **Test on the provided example**(s) — copy the sample input from the statement, run, compare output byte-for-byte\n2. **Test on extreme inputs** — generate worst-case inputs locally (max N, max values, all same, alternating, etc.) and verify timing and answer\n3. **Verify Python matches C++** — if you wrote both, run both on the same random inputs and `diff` the outputs. If they disagree, one is wrong (usually Python — overflow, edge case, off-by-one)\n4. **Check memory** — for N=10^6 with several long arrays, you can easily blow 64MB. Each `int` in Python is ~28 bytes; use `array('i', ...)` to get 4 bytes\u002Felement\n\nIf you can't get the original test data, **generate your own stress tests**. A correct slow brute-force compared against the fast solution catches most algorithmic bugs. See `references\u002Fstress-testing.md`.\n\n## Common pitfalls\n\n- **Integer overflow**: `N * (N-1) \u002F 2` overflows `int` for N ≥ ~65536. Use `long long` in C\u002FC++; in Python int is unbounded so no issue\n- **Off-by-one**: many problems use 1-indexing in the statement. Match it in the code or convert consistently\n- **freopen for named files**: pbinfo and Infoarena require `problema.in` \u002F `problema.out`. Codeforces uses stdin\u002Fstdout. LeetCode has no I\u002FO at all (function signature). Check before submitting\n- **printf vs cout speed**: for very large output, neither is fast enough. Use string buffer + fwrite\n- **Recursion stack**: most judges limit stack to 8MB; deep recursion (DFS on N=10^6) needs iterative rewrite or explicit stack\n- **Endianness\u002Fword size**: judges are 64-bit Linux. Hardcoded shellcode in Python (see pbinfo skill) assumes this\n- **PyPy vs CPython**: some judges offer both. PyPy is often 10× faster but has slower startup and different gotchas\n\n## Output expectations\n\nWhen the user asks for help, deliver:\n\n1. **One source file per requested language**, named after the problem (`problem.cpp`, `problem.c`, `problem.py`)\n2. A **brief explanation** of the algorithm — one or two paragraphs, not a wall of text\n3. **Local benchmark numbers** if you could test (e.g. \"N=10^6 in 140ms locally; should be ~300ms on the judge\")\n4. **Honest assessment** of expected score. If Python can only realistically score 65p instead of 100p without exotic tricks, say so. Don't promise AC if you're not sure.\n\nAlways use `present_files` to deliver the source files at the end so the user can download them.\n\n## References\n\nLoad these as needed (don't load them all upfront — they're substantial):\n\n- `references\u002Ftemplates\u002Ftemplate.cpp` — Production C++ template with FastScanner\n- `references\u002Ftemplates\u002Ftemplate.c` — Same in pure C (no STL)\n- `references\u002Ftemplates\u002Ftemplate.py` — Python template with FastScanner and array storage\n- `references\u002Fpython-speed.md` — Detailed Python performance techniques (digit-parity tricks, linear sieves, numpy when available, etc.)\n- `references\u002Falgorithm-cheatsheet.md` — Quick reference: what algorithm fits which constraint\n- `references\u002Fstress-testing.md` — How to verify correctness without judge test data\n- `references\u002Fjudges.md` — Quirks per judge (pbinfo, Codeforces, AtCoder, LeetCode, etc.)\n","# Competitive Programming Solver\n\nA skill for producing **correct and fast** solutions to algorithmic problems, in **C, C++, and Python**, across all major online judges.\n\nThe goal is not just to write code — it's to write code that **passes within the time limit on the judge's machine**, which is the only success criterion that actually matters in competitive programming.\n\n## When to use this skill\n\nUse whenever the user is solving a problem from an online judge or competition. Concrete triggers:\n\n- Names a judge: Codeforces, AtCoder, LeetCode, Infoarena, pbinfo, Kattis, SPOJ, USACO, HackerEarth, HackerRank, CSES, oj.uz, ICPC, IOI, etc.\n- Pastes a problem statement (input format, output format, constraints, time\u002Fmemory limits)\n- Shares an existing solution that gets TLE, WA, MLE, RE, or partial score\n- Asks for \"the fastest way to compute X\" with constraints like N ≤ 10^6\n- Talks about contests, olympiads, ranked rounds, or training\n\nIf the user is on **pbinfo.ro specifically and needs Python to pass within tight limits**, also load the companion skill `pbinfo-python-jit` — it adds shellcode JIT techniques specific to the pbinfo sandbox.\n\n## The five-phase workflow\n\nEvery problem follows the same phases. Do them in order, but don't skip ahead.\n\n### Phase 1: Understand the problem\n\nRead the statement carefully. Identify:\n\n- **What is asked**: one output, multiple queries, optimization, counting, decision?\n- **Input\u002Foutput format**: stdin\u002Fstdout, named files, special separators, multiple test cases?\n- **Constraints**: N, Q, values, time limit, memory limit, stack limit\n- **Edge cases**: N=1, all same, all distinct, max values, empty inputs\n\nFor pbinfo problems specifically: the I\u002FO is always named files (e.g. `problema.in` \u002F `problema.out`), not stdin\u002Fstdout.\n\nIf anything is unclear (especially the formula for \"type 2 queries\", the exact pairing convention \"ordered vs unordered\", or whether indices are 0- or 1-based), **ask the user** before writing code. Wrong formula = WA on all hard tests.\n\n### Phase 2: Pick the algorithm\n\nMatch the constraints to the algorithm class. This is the most important step.\n\n| N (or operations) | Allowed complexity (per second, C++) |\n|---|---|\n| ≤ 12 | O(N!) brute force \u002F bitmask |\n| ≤ 25 | O(2^N) meet in middle |\n| ≤ 500 | O(N^3) Floyd-Warshall, matrix DP |\n| ≤ 5000 | O(N^2) DP, edit distance |\n| ≤ 10^5 | O(N log N) sort, segment tree |\n| ≤ 10^6 | O(N) or O(N log log N) sieves, BFS, two pointers |\n| ≤ 10^7 | O(N) with low constant, mostly arithmetic |\n| ≤ 10^9 | O(log N) or O(√N) per query |\n\nPython is **5–20× slower** than C\u002FC++ depending on the workload. For Python plan for a constant of ~10×; if the C++ solution barely fits the time limit, Python likely needs an algorithmic shortcut or low-level tricks. See `references\u002Fpython-speed.md`.\n\nDocument the chosen algorithm briefly in a comment at the top of each source file, especially for Python. It helps debugging and helps the user understand.\n\n### Phase 3: Implement (C++ first)\n\n**Write C++ first**, even if the user wants Python. Reasons:\n1. Catches algorithm bugs quickly — C++ runs fast enough that you don't conflate \"slow\" with \"wrong\"\n2. Establishes the reference behavior against which Python \u002F C can be verified\n3. Most online judges run C++ at full speed, so this is the safest path to AC\n\nThe C++ template lives in `references\u002Ftemplates\u002Ftemplate.cpp`. Key features:\n- `FastScanner` class with `1 \u003C\u003C 20` byte buffer and inlined `readChar`\u002F`readInt`\n- `freopen` for named-file I\u002FO if the judge requires it\n- String-buffered output (`string out; out.reserve(Q*16); ... fwrite(...)`) — `printf` is too slow when Q is large\n- Avoid `std::endl` (flushes); use `'\\n'`\n- `using namespace std;` is fine for competitive programming\n\n### Phase 4: Implement C (if needed)\n\nSome judges accept only C (no C++). Some users want C for educational purposes. C is essentially C++ minus STL — port the C++ solution by replacing `vector` with raw `malloc`\u002F`free`, `string` with manual `char buf[]`, and `deque` with circular buffer arrays.\n\nTemplate: `references\u002Ftemplates\u002Ftemplate.c`.\n\n### Phase 5: Implement Python\n\nPython has two failure modes: **TLE** (algorithm is fine but pure Python overhead kills it) and **MLE** (allocating millions of Python int objects). Defenses:\n\n1. **Read in bulk** as bytes: `data = sys.stdin.buffer.read()`, parse with custom scanner over `bytes` (each byte is already an int 0–255, no decode needed)\n2. **Use `array.array`** (or `bytearray` for byte arrays) instead of lists for million-element numeric storage\n3. **Hoist locals**: in hot loops, `data = self.data; n = self.n; i = self.i` before the loop, write back at the end\n4. **Batch I\u002FO**: collect outputs in a list and `\"\\n\".join(out)` at the end; never `print(...)` in a loop with millions of iterations\n5. **Algorithmic shortcuts**: linear sieves, monotonic deques, sum-of-digit-parity via `sum(bytes(str(x), 'ascii')) & 1` (3× faster than `while x%10`)\n\nPython template: `references\u002Ftemplates\u002Ftemplate.py`. For deeper performance techniques and tricks specific to interpreted Python, see `references\u002Fpython-speed.md`.\n\nIf pure Python can't make the time limit and the user is on **pbinfo**, escalate to the companion skill `pbinfo-python-jit`, which uses shellcode-via-ctypes-mmap to run native x86-64 code from inside Python. It has consistently turned 35–65p Python solutions into 100p across a dozen problems.\n\n## Verification before submission\n\nFor every solution, before handing it to the user:\n\n1. **Test on the provided example**(s) — copy the sample input from the statement, run, compare output byte-for-byte\n2. **Test on extreme inputs** — generate worst-case inputs locally (max N, max values, all same, alternating, etc.) and verify timing and answer\n3. **Verify Python matches C++** — if you wrote both, run both on the same random inputs and `diff` the outputs. If they disagree, one is wrong (usually Python — overflow, edge case, off-by-one)\n4. **Check memory** — for N=10^6 with several long arrays, you can easily blow 64MB. Each `int` in Python is ~28 bytes; use `array('i', ...)` to get 4 bytes\u002Felement\n\nIf you can't get the original test data, **generate your own stress tests**. A correct slow brute-force compared against the fast solution catches most algorithmic bugs. See `references\u002Fstress-testing.md`.\n\n## Common pitfalls\n\n- **Integer overflow**: `N * (N-1) \u002F 2` overflows `int` for N ≥ ~65536. Use `long long` in C\u002FC++; in Python int is unbounded so no issue\n- **Off-by-one**: many problems use 1-indexing in the statement. Match it in the code or convert consistently\n- **freopen for named files**: pbinfo and Infoarena require `problema.in` \u002F `problema.out`. Codeforces uses stdin\u002Fstdout. LeetCode has no I\u002FO at all (function signature). Check before submitting\n- **printf vs cout speed**: for very large output, neither is fast enough. Use string buffer + fwrite\n- **Recursion stack**: most judges limit stack to 8MB; deep recursion (DFS on N=10^6) needs iterative rewrite or explicit stack\n- **Endianness\u002Fword size**: judges are 64-bit Linux. Hardcoded shellcode in Python (see pbinfo skill) assumes this\n- **PyPy vs CPython**: some judges offer both. PyPy is often 10× faster but has slower startup and different gotchas\n\n## Output expectations\n\nWhen the user asks for help, deliver:\n\n1. **One source file per requested language**, named after the problem (`problem.cpp`, `problem.c`, `problem.py`)\n2. A **brief explanation** of the algorithm — one or two paragraphs, not a wall of text\n3. **Local benchmark numbers** if you could test (e.g. \"N=10^6 in 140ms locally; should be ~300ms on the judge\")\n4. **Honest assessment** of expected score. If Python can only realistically score 65p instead of 100p without exotic tricks, say so. Don't promise AC if you're not sure.\n\nAlways use `present_files` to deliver the source files at the end so the user can download them.\n\n## References\n\nLoad these as needed (don't load them all upfront — they're substantial):\n\n- `references\u002Ftemplates\u002Ftemplate.cpp` — Production C++ template with FastScanner\n- `references\u002Ftemplates\u002Ftemplate.c` — Same in pure C (no STL)\n- `references\u002Ftemplates\u002Ftemplate.py` — Python template with FastScanner and array storage\n- `references\u002Fpython-speed.md` — Detailed Python performance techniques (digit-parity tricks, linear sieves, numpy when available, etc.)\n- `references\u002Falgorithm-cheatsheet.md` — Quick reference: what algorithm fits which constraint\n- `references\u002Fstress-testing.md` — How to verify correctness without judge test data\n- `references\u002Fjudges.md` — Quirks per judge (pbinfo, Codeforces, AtCoder, LeetCode, etc.)\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fcompetitive-programming-solver","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill competitive-programming-solver",{"tool":53,"command":54},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill competitive-programming-solver",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill competitive-programming-solver","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002FSKILL.md",true,[61,67,71,75,79,83,87,91],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"agents\u002Fopenai.yaml","REFERENCE","参考文档",235,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002Fagents\u002Fopenai.yaml",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Falgorithm-cheatsheet.md",3281,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002Freferences\u002Falgorithm-cheatsheet.md",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fjudges.md",3387,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002Freferences\u002Fjudges.md",{"path":76,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fpython-speed.md",6369,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002Freferences\u002Fpython-speed.md",{"path":80,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fstress-testing.md",2961,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002Freferences\u002Fstress-testing.md",{"path":84,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Ftemplates\u002Ftemplate.c",2026,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002Freferences\u002Ftemplates\u002Ftemplate.c",{"path":88,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Ftemplates\u002Ftemplate.cpp",2281,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002Freferences\u002Ftemplates\u002Ftemplate.cpp",{"path":92,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Ftemplates\u002Ftemplate.py","SCRIPT","脚本",2204,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcompetitive-programming-solver\u002Freferences\u002Ftemplates\u002Ftemplate.py",[98,119,150,177,191,206],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":36},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[105,106,107,108,109,110,111,112,113,32,114,115,116,117,118],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":130,"publishedAt":36},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[125],{"categoryNo":126,"categoryName":127,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[131,132,133,134,135,136,137,138,139,140,141,142,143,144,32,145,146,147,148,149],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":162,"publishedAt":36},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[156,159],{"categoryNo":157,"categoryName":158,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":160,"categoryName":161,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000008","测试与质量",[163,164,165,166,167,168,169,170,171,172,132,173,174,175,176],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":36},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[179,184,185,186,187,188,189,190],"setup","report","project","installation","project setup","issues","state",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":36},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[197],{"categoryNo":126,"categoryName":127,"taxonomyType":128,"taxonomyTypeDesc":129},[193,199,110,200,201,202,32,31,203,204,205],"start issue","issue","ready","work on issue","work","work on","development",{"skillNo":207,"name":184,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":36},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[184,186,147,212,188,213],"files","interactive"]